© 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. 5-CLT-HP
    7. 97992
    Prev
    Next
    INDEX
    Explanations

    ine

    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
    ValueStyle
    -0.62
    TagMode
    -0.57
     سكانية
    -0.56
    ContentAsync
    -0.56
     تضيفلها
    -0.56
     >=",
    -0.54
    Personensuche
    -0.54
    EndContext
    -0.53
     Chaldean
    -0.52
    AndEndTag
    -0.51
    POSITIVE LOGITS
     démocratie
    0.55
     szár
    0.48
    ijiet
    0.48
    entibus
    0.48
     skydd
    0.48
     récompense
    0.48
     vérit
    0.48
    frå
    0.48
     stabilité
    0.47
     frågor
    0.47
    Activations Density 0.000%

    No Known Activations