© 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. 1-CLT-HP
    7. 12149
    Prev
    Next
    INDEX
    Explanations

    programming characters

    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
     متعلقه
    -0.91
     AssemblyTitle
    -0.72
    SourceChecksum
    -0.60
     ISTAT
    -0.57
     offerts
    -0.57
    Rüyada
    -0.56
    xase
    -0.53
    fromnode
    -0.53
    <bos>
    -0.52
     الحره
    -0.51
    POSITIVE LOGITS
    apunov
    0.63
    tagHelperRunner
    0.56
    schild
    0.54
    buckle
    0.54
     \}
    0.52
     ± 
    0.51
     ¦
    0.50
    StartTag
    0.48
     literal
    0.48
    }-${
    0.47
    Activations Density 0.078%

    No Known Activations