© 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. 5-CLT-HP
    7. 92559
    Prev
    Next
    INDEX
    Explanations

    y

    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
    //
    -0.63
    GraphicsUnit
    -0.57
    awtextra
    -0.56
    mtrl
    -0.48
     ویکی‌پدیا
    -0.44
    >{"
    -0.44
    ashqai
    -0.44
    rizona
    -0.43
    Życiorys
    -0.43
    hounds
    -0.42
    POSITIVE LOGITS
    RegressionTest
    0.69
     pitä
    0.61
    Portail
    0.60
    jeta
    0.59
    ibrator
    0.56
    isp
    0.55
    hyrchwyd
    0.54
     lenti
    0.54
    ope
    0.53
    τια
    0.53
    Activations Density 0.006%

    No Known Activations