© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90977
    Prev
    Next
    INDEX
    Explanations

    code documentation

    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
    dillo
    -1.47
    eh
    -0.81
     eh
    -0.61
    σιν
    -0.50
     Tob
    -0.47
    ept
    -0.47
    ุง
    -0.45
     raccolta
    -0.45
    ága
    -0.43
    tymologie
    -0.43
    POSITIVE LOGITS
    bewerken
    0.86
    SourceChecksum
    0.81
    Personensuche
    0.81
    ScopeManager
    0.79
    uxxxx
    0.77
     Wikimedijinoj
    0.76
    RectangleBorder
    0.74
     referenties
    0.73
    InputTagHelper
    0.73
     Exacts
    0.72
    Activations Density 0.223%

    No Known Activations