© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 221
    Prev
    Next
    INDEX
    Explanations

    describing conditions

    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
    -0.99
    LookAnd
    -0.94
    featureID
    -0.92
    RectangleBorder
    -0.91
    RegistryLite
    -0.88
     beginnetje
    -0.85
    脚注の使い方
    -0.83
     Мексичка
    -0.82
     الرياضيه
    -0.82
     pinulongan
    -0.81
    POSITIVE LOGITS
    !
    0.52
    */
    0.47
    </em>
    0.47
    use
    0.45
    sel
    0.45
    干
    0.45
    ;
    0.44
     corresponden
    0.43
    extra
    0.43
    зю
    0.43
    Activations Density 0.013%

    No Known Activations