© 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. 3322
    Prev
    Next
    INDEX
    Explanations

    make

    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
     ***!
    -0.51
    ︎
    -0.49
     metu
    -0.47
     côtés
    -0.46
    Viki
    -0.46
    ategy
    -0.46
    ')));
    -0.46
    Any
    -0.44
    ξε
    -0.43
     mogelijk
    -0.43
    POSITIVE LOGITS
     mistakes
    0.83
     Mistakes
    0.74
    帖最后由
    0.71
     فريبيس
    0.65
    SequentialGroup
    0.64
     mistake
    0.62
    URLException
    0.59
     Mistake
    0.58
     failures
    0.57
     errors
    0.57
    Activations Density 0.005%

    No Known Activations