© 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. 656
    Prev
    Next
    INDEX
    Explanations

    data, technical snippets

    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
    ConstraintMaker
    -0.56
    #+#
    -0.52
    hysema
    -0.49
    ($__
    -0.47
     EnglishChoose
    -0.42
    WebVitals
    -0.41
    NameValuePair
    -0.41
     Vitale
    -0.40
    amship
    -0.40
    qxd
    -0.39
    POSITIVE LOGITS
    AntiForgeryToken
    0.66
    ніципалі
    0.64
    lą
    0.60
     المعيارى
    0.59
    ("/:
    0.57
    Filmographie
    0.56
    windowFixed
    0.56
     dichiarato
    0.56
    ')(
    0.55
    ubre
    0.54
    Activations Density 0.000%

    No Known Activations