© 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. 4-CLT-HP
    7. 4317
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
    Rè
    -0.60
    EndContext
    -0.58
    ulateur
    -0.54
    podar
    -0.53
    stateProvider
    -0.52
     FetchType
    -0.52
    Bid
    -0.52
     terce
    -0.51
    irah
    -0.50
    ManagedBean
    -0.50
    POSITIVE LOGITS
     yours
    0.57
     ours
    0.56
    AndEndTag
    0.55
     dieux
    0.52
     quelcon
    0.50
     réguli
    0.50
     vuoi
    0.49
     فريبيس
    0.48
     Ours
    0.48
     grecque
    0.48
    Activations Density 0.006%

    No Known Activations