© 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. 44122
    Prev
    Next
    INDEX
    Explanations

    take

    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
     (
    -0.44
    あれば
    -0.40
     us
    -0.40
     
    -0.39
    <bos>
    -0.35
     that
    -0.35
     provides
    -0.35
     veren
    -0.35
     me
    -0.34
     ندارد
    -0.34
    POSITIVE LOGITS
    tagHelper
    0.77
    ImageContext
    0.75
    ConfigureAwait
    0.73
     GoogleFonts
    0.72
     ModelExpression
    0.70
     tartalomajánló
    0.69
    SaveChangesAsync
    0.69
    enumi
    0.69
    BeginContext
    0.69
     تانيه
    0.69
    Activations Density 0.051%

    No Known Activations