© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 448
    Prev
    Next
    INDEX
    Explanations

    combinations

    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
     GenerationType
    -0.48
     alimentaires
    -0.46
     »)
    -0.44
     combination
    -0.44
     picioare
    -0.43
     combo
    -0.42
    äng
    -0.42
     pédagogique
    -0.41
    مصادر
    -0.41
     тобой
    -0.40
    POSITIVE LOGITS
    queryInterface
    0.80
    XMLSchema
    0.69
    PhysRev
    0.68
    WebElementEntity
    0.66
     يتيمه
    0.65
     EconPapers
    0.64
    shaft
    0.63
    plasia
    0.62
     sceptre
    0.62
    setVerticalGroup
    0.61
    Activations Density 0.002%

    No Known Activations