© 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. 500
    Prev
    Next
    INDEX
    Explanations

    acting

    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
     ModelExpression
    -0.57
    voorbeeld
    -0.44
    partimento
    -0.44
    setupUi
    -0.42
     बीच
    -0.41
    urized
    -0.40
     chi̍t
    -0.39
    Leod
    -0.38
    createObject
    -0.38
    ̙
    -0.38
    POSITIVE LOGITS
     ashore
    0.66
    %)$
    0.65
     invariants
    0.61
     alignments
    0.61
    ComponentName
    0.60
     SNR
    0.60
     crutches
    0.60
    Xna
    0.59
     monarchs
    0.59
     predators
    0.59
    Activations Density 0.037%

    No Known Activations