© 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. 5-CLT-HP
    7. 97301
    Prev
    Next
    INDEX
    Explanations

    failure

    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
    "/>
    -0.49
    ammen
    -0.41
    getSupport
    -0.40
     mínimos
    -0.40
     chwil
    -0.39
     himo
    -0.39
    '},
    -0.39
     collectivités
    -0.38
     logiciels
    -0.38
     mennesker
    -0.37
    POSITIVE LOGITS
     للمعارف
    0.79
    出版年
    0.76
    AutoScaleMode
    0.73
     مرئيه
    0.69
     الحره
    0.69
    principalTable
    0.68
     تضيفلها
    0.67
     صوتيه
    0.67
     was
    0.63
     مشين
    0.62
    Activations Density 0.002%

    No Known Activations