© 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. 9575
    Prev
    Next
    INDEX
    Explanations

    Scientific research

    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
     nahilalakip
    -0.85
    
    -0.84
    LookAnd
    -0.82
     AssemblyCulture
    -0.82
     ModelExpression
    -0.79
    +#+#
    -0.77
     للمعارف
    -0.76
     CreateTagHelper
    -0.73
     المعيارى
    -0.72
    WithIOException
    -0.71
    POSITIVE LOGITS
    ogado
    0.45
    lyst
    0.44
    łości
    0.44
    getSupport
    0.42
     methyl
    0.42
    チール
    0.42
    wachs
    0.41
     on
    0.41
     the
    0.41
    rücken
    0.41
    Activations Density 0.239%

    No Known Activations