© 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. 3333
    Prev
    Next
    INDEX
    Explanations

    as including

    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
     للاسماء
    -0.84
     وتسجيلات
    -0.81
    UnsafeEnabled
    -0.73
     يتيمه
    -0.70
    stateProvider
    -0.67
    Geplaatst
    -0.66
     playmobil
    -0.65
     HttpNotFound
    -0.65
    Datuak
    -0.63
     traités
    -0.63
    POSITIVE LOGITS
     those
    0.61
     ones
    0.59
     whether
    0.58
     the
    0.57
     enzymes
    0.54
     how
    0.52
     proteins
    0.49
     genes
    0.49
     molecules
    0.48
     sites
    0.45
    Activations Density 0.006%

    No Known Activations