© 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. 42951
    Prev
    Next
    INDEX
    Explanations

    shorter

    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
     "
    -0.83
    "
    -0.77
    <bos>
    -0.76
    verwijspagina
    -0.74
    "."
    -0.65
     "'
    -0.63
    "¿
    -0.62
     "[
    -0.60
    "'
    -0.60
    "…
    -0.60
    POSITIVE LOGITS
    RectangleBorder
    0.71
    StoreMessageInfo
    0.56
    ConstraintMaker
    0.53
     мәкал
    0.52
    帖最后由
    0.52
     enfans
    0.51
     hadapan
    0.50
    enumi
    0.50
    enumii
    0.50
     NSCoder
    0.50
    Activations Density 0.074%

    No Known Activations