© 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. 5-CLT-HP
    7. 1073
    Prev
    Next
    INDEX
    Explanations

    ruling

    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
     Cientí
    -0.43
    anglès
    -0.42
     onData
    -0.40
     Investigación
    -0.38
     seda
    -0.38
    ola
    -0.37
    とい
    -0.36
    has
    -0.36
    have
    -0.36
     existentes
    -0.36
    POSITIVE LOGITS
    MemoryWarning
    0.89
     Wiktionnaire
    0.81
    帖最后由
    0.75
     lenker
    0.75
    expandindo
    0.68
     виправивши
    0.68
     surla
    0.66
    windowFixed
    0.66
     كومونز
    0.66
    GEBURTSDATUM
    0.66
    Activations Density 0.000%

    No Known Activations