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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45478
    Prev
    Next
    INDEX
    Explanations

    food

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.91
    tvguidetime
    -0.71
    <bos>
    -0.71
     trajets
    -0.69
    CppCodeGen
    -0.67
     виправивши
    -0.67
     Theſe
    -0.65
     Roskov
    -0.65
     ModelExpression
    -0.64
    HasForeignKey
    -0.63
    POSITIVE LOGITS
     or
    0.46
    ண்டும்
    0.45
    Iden
    0.43
    ul
    0.42
     cour
    0.41
     progre
    0.39
     and
    0.39
     maupun
    0.39
    Salam
    0.38
    titel
    0.38
    Activations Density 0.007%

    No Known Activations