© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2405
    Prev
    Next
    INDEX
    Explanations

    have

    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
    OGND
    -0.79
    AndEndTag
    -0.78
    :+:
    -0.73
     BoxFit
    -0.71
     незавершена
    -0.68
     فريبيس
    -0.67
    VersionUID
    -0.66
     ویکی‌پدیای
    -0.65
     صوتيه
    -0.65
     quelcon
    -0.63
    POSITIVE LOGITS
     at
    0.71
     certain
    0.66
     means
    0.63
     sufficient
    0.62
     corresponding
    0.59
     adequate
    0.53
     just
    0.50
     a
    0.50
     ways
    0.50
     suitable
    0.48
    Activations Density 0.002%

    No Known Activations