© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1670
    Prev
    Next
    INDEX
    Explanations

    time-related expressions

    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
    50
    +0.14
    0.7%
    1376
    +0.13
    0.7%
    897
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.14
    0.07
    1376
    +0.13
    0.06
    1013
    +0.12
    0.06
    Negative Logits
    <bos>
    -2.12
    ⓧ
    -0.70
     onBackPressed
    -0.58
     државе
    -0.58
     promote
    -0.56
     inform
    -0.55
     cre
    -0.54
     насеља
    -0.53
     مرئيه
    -0.52
    /*++
    -0.51
    POSITIVE LOGITS
     lidl
    1.22
     affor
    1.22
     fatis
    1.19
     sovere
    1.19
     nomine
    1.15
     unlaw
    1.13
     michelin
    1.12
     erik
    1.08
     wien
    1.08
     stockholm
    1.08
    Activations Density 0.314%

    No Known Activations