© 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. 94837
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     enfans
    -0.60
    tvguidetime
    -0.52
     Jefus
    -0.50
     groote
    -0.49
     turg
    -0.49
     &_
    -0.47
     Etats
    -0.47
     maniere
    -0.47
    ünst
    -0.47
     NACIONAL
    -0.46
    POSITIVE LOGITS
     (
    0.80
    .
    0.71
    ,
    0.61
    (
    0.58
    —
    0.57
     is
    0.56
     AssemblyCompany
    0.54
    ."
    0.51
    .,
    0.50
    帖最后由
    0.50
    Activations Density 2.103%

    No Known Activations