© 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. 5-CLT-HP
    7. 1995
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency

    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
     متعلقه
    -0.48
     alapján
    -0.47
     treat
    -0.41
    interopRequire
    -0.41
     calldata
    -0.40
     समीक्षाएं
    -0.40
    peño
    -0.39
     cause
    -0.38
    kuuta
    -0.38
    //
    -0.38
    POSITIVE LOGITS
    EndGlobalSection
    0.82
     Often
    0.70
    often
    0.68
     Usually
    0.65
     Oft
    0.63
     often
    0.62
     and
    0.62
    mtrl
    0.61
    Often
    0.60
    +#+#
    0.59
    Activations Density 0.019%

    No Known Activations