© 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. 5-CLT-HP
    7. 1088
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     ModelExpression
    -0.98
    EndProject
    -0.88
     HasFactory
    -0.87
     kasarigan
    -0.85
    ContentAsync
    -0.83
     AspNetCore
    -0.81
    setViewportView
    -0.81
    spesies
    -0.81
    EndGlobalSection
    -0.80
    )».
    -0.79
    POSITIVE LOGITS
    .
    0.36
     KeyError
    0.36
    readObject
    0.35
    חת
    0.35
    prnewswire
    0.35
    غ
    0.33
    kra
    0.33
    hava
    0.33
     ra
    0.33
     hale
    0.32
    Activations Density 0.017%

    No Known Activations