© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92067
    Prev
    Next
    INDEX
    Explanations

    th

    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
    enumi
    -0.66
    ()]);
    -0.60
    th
    -0.57
    !”.
    -0.56
     moulds
    -0.56
     ''}
    -0.55
    kháu
    -0.55
    ">)</
    -0.54
    )』
    -0.53
    ...>
    -0.53
    POSITIVE LOGITS
     autorytatywna
    1.00
    routeProvider
    0.63
    principalColumn
    0.61
    ⓧ
    0.60
    mybatisplus
    0.60
    Viited
    0.57
    
    0.57
     nahilalakip
    0.56
    Tembelea
    0.55
    msgSender
    0.54
    Activations Density 0.324%

    No Known Activations