© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94920
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     Few
    -0.64
    Some
    -0.63
     Some
    -0.61
     can
    -0.61
    Few
    -0.60
     few
    -0.57
    Despite
    -0.55
     Despite
    -0.54
    Even
    -0.52
     Certainly
    -0.51
    POSITIVE LOGITS
     виправивши
    0.85
     Roskov
    0.84
    PreferredItem
    0.78
     Wikimedijinoj
    0.77
     Shakspeare
    0.76
     Majefty
    0.75
     againſt
    0.73
    OGND
    0.71
     Houſe
    0.71
     Mahomet
    0.71
    Activations Density 0.011%

    No Known Activations