© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41081
    Prev
    Next
    INDEX
    Explanations

    expose reveal

    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
     reveal
    -0.78
    migrationBuilder
    -0.67
    WaitGroup
    -0.64
    DataBind
    -0.61
    OrBuilder
    -0.59
     expose
    -0.59
    isnan
    -0.58
    reveal
    -0.58
    UINTN
    -0.57
     announcement
    -0.56
    POSITIVE LOGITS
    ScopeManager
    0.73
     oprot
    0.71
    ity
    0.60
     ویکی‌پدی
    0.58
    oa̍t
    0.56
    TagMode
    0.54
     дописавши
    0.53
    omeness
    0.53
    ability
    0.52
    ize
    0.52
    Activations Density 0.036%

    No Known Activations