© 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. 3383
    Prev
    Next
    INDEX
    Explanations

    sports summaries

    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
     record
    -0.75
    record
    -0.65
    recorded
    -0.65
     RECORD
    -0.61
    RECORD
    -0.60
    recording
    -0.58
    レコード
    -0.57
     recording
    -0.57
     Recording
    -0.54
    Record
    -0.52
    POSITIVE LOGITS
    TestTools
    0.59
     >=",
    0.59
     ExecuteAsync
    0.59
    kuuta
    0.57
    endpush
    0.55
    lunda
    0.55
     muualla
    0.54
     estimés
    0.53
    IconModule
    0.53
    MENAFN
    0.52
    Activations Density 0.006%

    No Known Activations