© 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. 5-CLT-HP
    7. 4877
    Prev
    Next
    INDEX
    Explanations

    book

    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
    ingdon
    -0.59
     sơ
    -0.53
     Lus
    -0.52
    ph
    -0.52
     Overseas
    -0.51
    himovic
    -0.51
    Otras
    -0.47
    ovsk
    -0.46
    thy
    -0.46
    OMEN
    -0.46
    POSITIVE LOGITS
    ScopeManager
    0.69
     समीक्षक
    0.66
     Houſe
    0.61
     houſe
    0.58
    XtraReports
    0.57
     nahilalakip
    0.56
    ValueStyle
    0.56
    ]){
    0.55
    ंदीखरीदारी
    0.53
    ImageContext
    0.52
    Activations Density 0.000%

    No Known Activations