© 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. 77849
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    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
    StoreMessageInfo
    -0.82
     gawas
    -0.73
    mergeFrom
    -0.71
     resourceCulture
    -0.68
    RUnlock
    -0.66
    GeoNames
    -0.66
    Хьажоргаш
    -0.65
    djangoproject
    -0.64
     насељу
    -0.64
    TintMode
    -0.63
    POSITIVE LOGITS
    Personendaten
    0.52
     MyBatis
    0.52
     الاطلاع
    0.47
     sapere
    0.44
     p
    0.42
     m
    0.41
     та
    0.40
    mybatisplus
    0.38
    Ground
    0.37
     t
    0.37
    Activations Density 0.000%

    No Known Activations