© 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. 1046
    Prev
    Next
    INDEX
    Explanations

    to into

    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
    dubbo
    -0.52
    хьтан
    -0.51
    Personendaten
    -0.50
    addCriterion
    -0.50
    picasso
    -0.49
     propOrder
    -0.48
    ELINES
    -0.48
    abon
    -0.48
     cómo
    -0.48
    URLException
    -0.47
    POSITIVE LOGITS
     a
    0.76
    GEBURTSDATUM
    0.59
     JpaRepository
    0.57
     an
    0.56
    extAlignment
    0.52
    urlpatterns
    0.52
    tvguidetime
    0.52
    providedIn
    0.51
     or
    0.51
    entyfik
    0.51
    Activations Density 0.016%

    No Known Activations