© 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. 3297
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    Autoritní
    -0.59
    पया
    -0.55
    <bos>
    -0.53
    SERIES
    -0.53
    buah
    -0.52
    9
    -0.50
     HasFactory
    -0.50
     petition
    -0.48
    βολ
    -0.46
    ுகள்
    -0.45
    POSITIVE LOGITS
    بوابة
    0.71
     InputDecoration
    0.70
     defaultstate
    0.67
    enumi
    0.60
    AndEndTag
    0.59
    发表于
    0.59
    жнему
    0.59
     Brice
    0.58
    ślę
    0.56
    Skocz
    0.55
    Activations Density 0.012%

    No Known Activations