© 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. 0-CLT-HP
    7. 42195
    Prev
    Next
    INDEX
    Explanations

    variety

    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
     grapes
    -0.94
    ValueStyle
    -0.94
     Horses
    -0.93
     Efq
    -0.92
    +#+#
    -0.91
     estimés
    -0.90
    RenderAtEndOf
    -0.90
    PhysRev
    -0.90
     horses
    -0.86
    argout
    -0.85
    POSITIVE LOGITS
     of
    0.68
     dem
    0.48
    io
    0.47
     
    0.47
    s
    0.47
     Mil
    0.44
    e
    0.44
     $
    0.44
    ی
    0.44
     Joseph
    0.42
    Activations Density 1.270%

    No Known Activations