© 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. 38900
    Prev
    Next
    INDEX
    Explanations

    emissions

    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
    MigrationBuilder
    -1.21
    LookAnd
    -1.05
    ValueStyle
    -1.03
     himo
    -1.00
     ComVisible
    -1.00
     CreateTagHelper
    -0.98
     emissions
    -0.94
    UVWXYZ
    -0.93
     HasFactory
    -0.93
    RenderAtEndOf
    -0.93
    POSITIVE LOGITS
     to
    0.56
     in
    0.51
    .
    0.51
    ,
    0.48
     (
    0.47
    :
    0.47
     broad
    0.46
     that
    0.43
     into
    0.43
     for
    0.41
    Activations Density 1.508%

    No Known Activations