© 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. 4-CLT-HP
    7. 4460
    Prev
    Next
    INDEX
    Explanations

    sheep

    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
     épaules
    -0.64
    ValueStyle
    -0.62
     rodillas
    -0.58
    easeOut
    -0.57
     lèvres
    -0.55
     oreilles
    -0.55
     émotions
    -0.54
    basicConfig
    -0.54
    elemField
    -0.53
     traités
    -0.52
    POSITIVE LOGITS
    crites
    0.74
    inaires
    0.69
     favorites
    0.65
    arians
    0.64
    toppers
    0.63
    ardians
    0.63
     per
    0.59
    letons
    0.59
     persons
    0.58
     attendants
    0.58
    Activations Density 0.020%

    No Known Activations