© 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. 1-CLT-HP
    7. 15570
    Prev
    Next
    INDEX
    Explanations

    data

    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
    SequentialGroup
    -0.68
     Réponses
    -0.63
     HasFactory
    -0.59
    ViewFeatures
    -0.57
     بيها
    -0.56
    findpost
    -0.56
    AnchorStyles
    -0.54
     ExecuteAsync
    -0.53
     للمعارف
    -0.52
     preprint
    -0.50
    POSITIVE LOGITS
    +#+
    0.71
    LookAnd
    0.51
    Products
    0.48
    grand
    0.47
     producto
    0.46
    noin
    0.45
    operand
    0.45
    流
    0.45
    ="#"><
    0.45
    CONCURRENT
    0.44
    Activations Density 0.045%

    No Known Activations