© 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. 1-CLT-HP
    7. 493
    Prev
    Next
    INDEX
    Explanations

    Returning

    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
     OFDb
    -0.71
     للاسماء
    -0.66
     الحره
    -0.60
    ค์
    -0.59
     springfox
    -0.58
    zeitige
    -0.56
    UMBUS
    -0.54
    ections
    -0.54
    ocarditis
    -0.53
    WebVitals
    -0.52
    POSITIVE LOGITS
    <bos>
    0.99
     to
    0.66
    ">—
    0.61
    ніципа
    0.47
    httphttps
    0.47
     simply
    0.47
     unpublished
    0.46
    ToMany
    0.46
     effectively
    0.46
    ActionCreators
    0.45
    Activations Density 0.404%

    No Known Activations