© 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. 12-RES-MATRYOSHKA-DC
    7. 10796
    Prev
    Next
    INDEX
    Explanations

    numeric values and their variations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    orteur
    -0.68
    migrationBuilder
    -0.63
     estekak
    -0.60
    Przypisy
    -0.59
    BeginContext
    -0.59
    SequentialGroup
    -0.57
    IntoConstraints
    -0.57
    Становништво
    -0.56
     regeringen
    -0.56
     inoxydable
    -0.53
    POSITIVE LOGITS
     eventdata
    0.54
    djangoproject
    0.53
    TagMode
    0.47
    lark
    0.46
    וויק
    0.46
    дца
    0.45
     onOptions
    0.45
    évaluateur
    0.45
    Disse
    0.45
     hObject
    0.44
    Activations Density 0.004%

    No Known Activations