© 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. 77394
    Prev
    Next
    INDEX
    Explanations

    emphasis

    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
     Administrativna
    -0.84
     فريبيس
    -0.80
     nahilalakip
    -0.79
    TypedDataSet
    -0.74
    RenderAtEndOf
    -0.71
     Roskov
    -0.71
     PeEnEo
    -0.71
     noDo
    -0.71
    Rhestr
    -0.70
     ProtoMessage
    -0.69
    POSITIVE LOGITS
     a
    0.77
     really
    0.68
    really
    0.50
    Really
    0.49
    ,
    0.49
     at
    0.48
     Really
    0.44
     effectively
    0.43
     realmente
    0.43
     REALLY
    0.43
    Activations Density 0.001%

    No Known Activations