© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10953
    Prev
    Next
    INDEX
    Explanations

    Legal and evidence

    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
     تضيفلها
    -0.88
    <bos>
    -0.88
     HasFactory
    -0.79
     للمعارف
    -0.75
    ỡng
    -0.70
     nahilalakip
    -0.69
    المناصب
    -0.69
    хьтан
    -0.69
     onPostExecute
    -0.68
     betweenstory
    -0.68
    POSITIVE LOGITS
    Aggregator
    0.49
    spunk
    0.49
     evidencia
    0.48
    UnknownFields
    0.47
     disobey
    0.47
    />";
    0.46
     affidavits
    0.46
     ilmo
    0.46
     testimony
    0.46
    aggreg
    0.46
    Activations Density 0.362%

    No Known Activations