© 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. 1003
    Prev
    Next
    INDEX
    Explanations

    founded

    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
     myſelf
    -1.03
    ſelf
    -1.00
     uſed
    -0.97
     étoient
    -0.97
     étoit
    -0.96
     itſelf
    -0.95
     الرياضيه
    -0.95
    ^(@)
    -0.95
     avoient
    -0.94
     houſe
    -0.93
    POSITIVE LOGITS
     in
    0.75
     on
    0.66
     via
    0.59
    .
    0.58
     from
    0.56
     so
    0.50
    :
    0.48
     for
    0.47
     far
    0.47
     due
    0.46
    Activations Density 0.106%

    No Known Activations