© 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. 95059
    Prev
    Next
    INDEX
    Explanations

    gam

    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
     gam
    -1.20
    gam
    -1.15
    Gam
    -1.13
     Game
    -1.06
    GAM
    -1.06
     Gam
    -1.05
     game
    -1.01
    game
    -0.98
    Game
    -0.98
     GAM
    -0.91
    POSITIVE LOGITS
    m
    0.66
     Efq
    0.51
    VertexAttrib
    0.49
     gddr
    0.49
     crystallization
    0.48
     crystall
    0.48
     plagioclase
    0.48
    ✭✭
    0.47
    ChildScrollView
    0.46
     Shakspeare
    0.46
    Activations Density 0.154%

    No Known Activations