© 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. 9532
    Prev
    Next
    INDEX
    Explanations

    oil or lib

    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
    addCriterion
    -0.63
    nocache
    -0.59
    parsedMessage
    -0.57
    addContainerGap
    -0.56
    Geplaatst
    -0.54
    hyrchwyd
    -0.50
    InitVars
    -0.50
     kär
    -0.49
     hObject
    -0.48
    fjspx
    -0.48
    POSITIVE LOGITS
    出版年
    0.67
    \{\\
    0.63
    ]--;
    0.57
     flamme
    0.56
    WidgetItem
    0.55
    tlement
    0.54
    Rcpp
    0.54
     }</
    0.54
    ']->
    0.54
    tschafts
    0.53
    Activations Density 0.021%

    No Known Activations