© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 2510
    Prev
    Next
    INDEX
    Explanations

    locations or names of places with the word "Hart."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    896
    +0.20
    1.1%
    313
    +0.18
    1.0%
    528
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.20
    0.03
    1097
    +0.18
    0.05
    1896
    +0.16
    0.03
    Negative Logits
    <bos>
    -0.69
     Luxemburg
    -0.60
    huber
    -0.59
     buk
    -0.59
    twimg
    -0.58
     Christiane
    -0.57
     Jochen
    -0.56
    konos
    -0.56
     Nugent
    -0.56
     Amazonas
    -0.56
    POSITIVE LOGITS
     Hart
    1.09
    Hart
    0.89
     répon
    0.84
     Février
    0.83
     pymysql
    0.80
     HART
    0.77
     Décembre
    0.75
     aprilie
    0.74
     ianuarie
    0.74
     februarie
    0.73
    Activations Density 0.531%

    No Known Activations