© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43257
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     ModelExpression
    -1.32
     CreateTagHelper
    -1.31
     AssemblyCulture
    -1.30
     Efq
    -1.30
     незавершена
    -1.30
    脚注の使い方
    -1.30
     nakalista
    -1.29
    __':
    
    -1.27
    NUMX
    -1.25
    AddTagHelper
    -1.23
    POSITIVE LOGITS
    i
    0.95
    e
    0.88
    ,
    0.87
    -
    0.80
    a
    0.79
     or
    0.76
     
    0.75
    .
    0.75
     and
    0.74
    /
    0.74
    Activations Density 0.046%

    No Known Activations