© 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. 92001
    Prev
    Next
    INDEX
    Explanations

    win

    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
     ویکی‌پدیا
    -0.82
    DoubleQuotes
    -0.73
     Référence
    -0.66
     '\\;'
    -0.66
    delwed
    -0.65
     frattempo
    -0.63
    BeginContext
    -0.62
     referenties
    -0.61
     Roskov
    -0.59
    Географиясе
    -0.58
    POSITIVE LOGITS
    onAttach
    0.48
     the
    0.48
     its
    0.47
    FirstResponder
    0.45
    ])->
    0.44
     their
    0.44
    аз
    0.44
    parsedMessage
    0.44
    рович
    0.44
    oide
    0.43
    Activations Density 0.028%

    No Known Activations