© 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. 20-CLT-HP
    7. 72289
    Prev
    Next
    INDEX
    Explanations

    takes

    np_max-act-logits · 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
    writeFieldEnd
    -1.06
    Personensuche
    -1.02
    LEncoder
    -0.94
     للاسماء
    -0.93
     disambiguazione
    -0.91
    parsedMessage
    -0.89
    MessageOf
    -0.88
     Réponses
    -0.88
    RectangleBorder
    -0.87
     HasFactory
    -0.86
    POSITIVE LOGITS
    al
    0.43
     home
    0.41
    th
    0.39
     from
    0.39
     out
    0.38
     Hütte
    0.37
    allow
    0.36
     joints
    0.36
     joint
    0.36
     as
    0.35
    Activations Density 0.005%

    No Known Activations