© 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. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1606
    Prev
    Next
    INDEX
    Explanations

    first-person statements

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     were
    -0.80
    RenderAtEndOf
    -0.78
     فريبيس
    -0.73
    >*/
    -0.72
    ագրություններ
    -0.72
     समीक्षाओं
    -0.71
     wanted
    -0.69
     had
    -0.69
    évaluateur
    -0.69
    <?>
    -0.68
    POSITIVE LOGITS
     guess
    0.83
     bet
    0.68
    guess
    0.68
     Guess
    0.66
     personally
    0.62
     imagine
    0.62
    Guess
    0.60
     scom
    0.60
     speculate
    0.60
     doubt
    0.59
    Activations Density 0.538%

    No Known Activations