© 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. 96289
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    itinéraire
    -0.43
     @"/
    -0.42
     scorso
    -0.42
    GetAxis
    -0.42
    cvtColor
    -0.42
    tvguidetime
    -0.42
    @{
    -0.41
    ⓧ
    -0.41
    GraphicsUnit
    -0.40
     transfieras
    -0.40
    POSITIVE LOGITS
    parsedMessage
    0.64
     kaynağından
    0.64
    PerformLayout
    0.63
    ährlich
    0.63
     contextLoads
    0.60
    Partager
    0.58
    ően
    0.58
    FundMe
    0.57
     décou
    0.55
    .*")]
    0.55
    Activations Density 0.025%

    No Known Activations