© 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. 38796
    Prev
    Next
    INDEX
    Explanations

    long

    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
    ary
    -0.61
    <eos>
    -0.59
    ful
    -0.54
    ous
    -0.54
    ↵↵↵
    -0.52
    ↵↵
    -0.50
    ARY
    -0.50
     of
    -0.50
    ry
    -0.50
    way
    -0.47
    POSITIVE LOGITS
     Efq
    1.10
     ſche
    0.96
     auffi
    0.93
     itſelf
    0.93
     iſt
    0.92
     ſch
    0.92
     ſeveral
    0.91
    RetentionPolicy
    0.91
     becauſe
    0.90
     myſelf
    0.90
    Activations Density 0.066%

    No Known Activations