Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31385
    Prev
    Next
    INDEX
    Explanations

    lines in a legal document that begin with an asterisk

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     or
    -0.78
    </em>
    -0.72
      
    -0.71
     (
    -0.71
     in
    -0.69
     -
    -0.68
    </i>
    -0.67
     
    -0.60
     le
    -0.60
     partial
    -0.59
    POSITIVE LOGITS
    berdayakan
    1.02
    expandindo
    1.02
     Majefty
    0.98
     Efq
    0.97
     فريبيس
    0.97
     propOrder
    0.91
     itſelf
    0.91
     auffi
    0.91
     raiſ
    0.91
     Reſ
    0.91
    Activations Density 0.007%

    No Known Activations