© 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. 0-CLT-HP
    7. 91957
    Prev
    Next
    INDEX
    Explanations

    introductions

    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
     Sack
    -0.55
     Shard
    -0.46
    Dash
    -0.46
    omotor
    -0.46
    Sack
    -0.45
    angan
    -0.44
     Sae
    -0.44
     attendre
    -0.44
    iets
    -0.43
    stones
    -0.43
    POSITIVE LOGITS
    titleMargin
    0.77
    Personendaten
    0.69
    PreferredItem
    0.66
    triangleq
    0.63
    PreExecute
    0.63
     MainAxisSize
    0.63
     يتيمه
    0.61
     članak
    0.61
    queryInterface
    0.60
    tvguidetime
    0.59
    Activations Density 1.012%

    No Known Activations