© 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. 90974
    Prev
    Next
    INDEX
    Explanations

    physical sensations

    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
     contextLoads
    -1.13
     فريبيس
    -1.11
     itſelf
    -1.07
     myſelf
    -1.04
     تضيفلها
    -0.96
    EndContext
    -0.95
     ſche
    -0.95
    ThroughAttribute
    -0.94
    RegressionTest
    -0.93
     auffi
    -0.91
    POSITIVE LOGITS
    .
    0.65
    ,
    0.61
     of
    0.57
    :
    0.56
    '
    0.56
     or
    0.52
    ’
    0.51
    -
    0.50
     in
    0.49
     for
    0.49
    Activations Density 0.828%

    No Known Activations