© 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. 4469
    Prev
    Next
    INDEX
    Explanations

    specifications

    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
    ConverterFactory
    -0.70
    
    -0.67
    )++;
    -0.63
    :+:
    -0.61
     cytok
    -0.60
    Дереккөздер
    -0.60
     Katrin
    -0.59
    UIControlState
    -0.59
    DrawerLayout
    -0.57
     Familienname
    -0.57
    POSITIVE LOGITS
     referenties
    0.55
     mitä
    0.53
     whom
    0.48
     what
    0.47
     who
    0.47
    whom
    0.46
     مُعرِّف
    0.43
    rawDesc
    0.42
    geen
    0.41
    raszamy
    0.41
    Activations Density 0.009%

    No Known Activations