© 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. 45306
    Prev
    Next
    INDEX
    Explanations

    e

    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
    eg
    -0.91
    eing
    -0.79
    e
    -0.78
    eed
    -0.69
     Efq
    -0.68
     Савезне
    -0.67
    ]--;
    -0.66
     Majefty
    -0.66
    eger
    -0.64
     Wikimedijinoj
    -0.63
    POSITIVE LOGITS
    ,
    0.56
    ъм
    0.50
    awtextra
    0.49
     (
    0.48
     head
    0.48
     on
    0.47
     in
    0.46
     task
    0.46
    m
    0.46
     I
    0.46
    Activations Density 0.048%

    No Known Activations