© 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. 1-CLT-HP
    7. 45820
    Prev
    Next
    INDEX
    Explanations

    all

    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
    Geplaatst
    -0.79
     nahilalakip
    -0.62
    ElementException
    -0.57
    Хьажоргаш
    -0.55
    OGND
    -0.54
    клопе
    -0.54
    PageRoute
    -0.53
    ed
    -0.51
    SharedDtor
    -0.50
    raisemb
    -0.50
    POSITIVE LOGITS
     Correct
    0.54
    Erfolge
    0.52
    linger
    0.48
    :+:
    0.48
    illac
    0.48
    defaultProps
    0.48
    awsze
    0.47
     Профиль
    0.47
    offsetof
    0.47
    SEGUIR
    0.47
    Activations Density 0.006%

    No Known Activations