© 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. 45143
    Prev
    Next
    INDEX
    Explanations

    how

    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
     how
    -0.63
     BoxDecoration
    -0.61
     = 
    -0.57
    granate
    -0.56
    AndEndTag
    -0.55
    )».
    -0.52
    awaiter
    -0.52
    ."</
    -0.52
    cnica
    -0.51
    \{\\
    -0.51
    POSITIVE LOGITS
    <bos>
    0.74
    InjectAttribute
    0.59
    ed
    0.54
    Välislingid
    0.53
    otum
    0.48
    RegressionTest
    0.48
     ostavi
    0.46
    rungsseite
    0.45
     propOrder
    0.45
     to
    0.44
    Activations Density 0.039%

    No Known Activations