© 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. 12992
    Prev
    Next
    INDEX
    Explanations

    ing

    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
    ver
    -0.48
     managing
    -0.43
     needing
    -0.38
     proving
    -0.37
    row
    -0.35
    md
    -0.35
     overcoming
    -0.34
     habiendo
    -0.34
     choosing
    -0.34
    age
    -0.34
    POSITIVE LOGITS
    CppMethod
    0.88
     متعلقه
    0.88
    addCriterion
    0.81
     myſelf
    0.79
    ſelf
    0.78
     Ahead
    0.77
     onOptions
    0.76
    ^(@)
    0.76
    رشف
    0.75
     Lights
    0.74
    Activations Density 0.136%

    No Known Activations