© 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. 23255
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "final."

    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
    EndPoint
    -0.67
    kend
    -0.66
    Ends
    -0.65
    endu
    -0.64
    end
    -0.63
    END
    -0.62
    sinon
    -0.60
    eschön
    -0.57
     Ends
    -0.57
    enders
    -0.56
    POSITIVE LOGITS
    出版年
    1.10
     ModelExpression
    0.96
     DialogInterface
    0.92
     mosaics
    0.88
     MatDialog
    0.87
     líquida
    0.87
    bootstrapcdn
    0.86
    Parameteri
    0.86
     ſche
    0.85
     Tirana
    0.85
    Activations Density 0.014%

    No Known Activations