© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1281
    Prev
    Next
    INDEX
    Explanations

    War

    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
     held
    -0.51
    انيف
    -0.49
     collapsed
    -0.48
    SourceChecksum
    -0.48
     rejected
    -0.47
    misi
    -0.47
     transpired
    -0.47
     gradi
    -0.46
    kijk
    -0.46
    Personensuche
    -0.46
    POSITIVE LOGITS
     mergeFrom
    0.72
    Hochspringen
    0.68
     AspNetCore
    0.68
     ब्रेकडाउन
    0.66
    enumi
    0.65
    SPATH
    0.63
    Демографія
    0.63
    Jeografia
    0.62
    Билгалдахарш
    0.61
     LUMP
    0.61
    Activations Density 0.003%

    No Known Activations