© 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. 77558
    Prev
    Next
    INDEX
    Explanations

    complete

    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
    IsMutable
    -0.75
     mourir
    -0.73
     médicaux
    -0.72
    MLLoader
    -0.69
    tonode
    -0.66
     ciudadana
    -0.66
     scolaires
    -0.64
     sauvages
    -0.63
    tanleria
    -0.63
     giudi
    -0.62
    POSITIVE LOGITS
    ,
    0.96
     When
    0.69
     Due
    0.56
     Once
    0.54
    \{\\
    0.54
     when
    0.53
     While
    0.53
    When
    0.52
     Wherever
    0.51
     note
    0.51
    Activations Density 0.000%

    No Known Activations