© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92001
    Prev
    Next
    INDEX
    Explanations

    ordinary/throughout

    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
    ordinary
    -0.92
     Throughout
    -0.75
    Throughout
    -0.71
    throughout
    -0.71
     throughout
    -0.71
    Ordinary
    -0.68
    зулта
    -0.67
    ized
    -0.66
     ordinary
    -0.63
    Vidite
    -0.61
    POSITIVE LOGITS
     the
    1.06
     our
    0.74
     what
    0.72
     its
    0.71
     your
    0.68
     their
    0.68
     how
    0.63
     a
    0.61
     his
    0.59
    ResponseWriter
    0.56
    Activations Density 0.026%

    No Known Activations