© 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. 40041
    Prev
    Next
    INDEX
    Explanations

    research topics

    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
    enumii
    -0.46
    akuya
    -0.46
    bows
    -0.45
    ślę
    -0.44
    clickable
    -0.44
    tiennent
    -0.43
    BATH
    -0.43
     referrerpolicy
    -0.43
     rayures
    -0.43
    жнему
    -0.42
    POSITIVE LOGITS
     of
    1.06
    AndroidJUnit
    0.69
    mybatisplus
    0.67
     nay
    0.63
    openzeppelin
    0.63
     الرياضيه
    0.62
    PreferredItem
    0.60
    NewUrlParser
    0.57
     zirc
    0.56
    nO
    0.56
    Activations Density 0.090%

    No Known Activations