© 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. 0-CLT-HP
    7. 1262
    Prev
    Next
    INDEX
    Explanations

    starting actions

    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
    :✨
    -0.82
    CloseOperation
    -0.66
     oprot
    -0.63
    OGND
    -0.57
     disambiguazione
    -0.57
     Caus
    -0.57
    tagHelperRunner
    -0.55
    %?
    -0.55
    UnsafeEnabled
    -0.54
    kháu
    -0.52
    POSITIVE LOGITS
    +:+
    0.62
     try
    0.61
    DeleteMapping
    0.58
     just
    0.57
     calling
    0.56
    mappedBy
    0.55
    breviations
    0.52
    reactstrap
    0.52
    Referències
    0.51
    tedt
    0.51
    Activations Density 0.036%

    No Known Activations