© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2600
    Prev
    Next
    INDEX
    Explanations

    phrases related to the care and maintenance of leather products

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    966
    +0.09
    0.3%
    1044
    +0.07
    0.2%
    1575
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1366
    +0.09
    0.02
    312
    +0.07
    0.02
    1203
    +0.07
    0.02
    Negative Logits
     Revolución
    -0.57
     kræ
    -0.52
     leaped
    -0.52
    export
    -0.51
    cần
    -0.50
     bezpiecze
    -0.50
    public
    -0.50
    Đi
    -0.48
    làm
    -0.48
    |}{\
    -0.47
    POSITIVE LOGITS
     neutral
    3.34
     Neutral
    3.21
    neutral
    3.00
    Neutral
    2.95
     neutrals
    2.65
     neutrality
    2.47
     neutr
    2.45
     Neutr
    2.28
     neutre
    2.23
    UTRAL
    1.91
    Activations Density 0.192%

    No Known Activations