© 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. 94973
    Prev
    Next
    INDEX
    Explanations

    I

    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
     amitié
    -0.66
     épu
    -0.61
     dignité
    -0.60
     élas
    -0.60
     pouvoirs
    -0.60
    зулта
    -0.59
     excès
    -0.59
     Information
    -0.59
     courants
    -0.58
    borderSide
    -0.56
    POSITIVE LOGITS
    <bos>
    0.75
     AssemblyCulture
    0.65
    )))),
    0.52
    tagHelperRunner
    0.50
    IsMutable
    0.49
    openzeppelin
    0.48
     whirlwind
    0.47
    ôm
    0.47
     rusty
    0.46
    силання
    0.45
    Activations Density 0.024%

    No Known Activations