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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3616
    Prev
    Next
    INDEX
    Explanations

    legal/financial issues

    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
    mappedBy
    -0.58
    KommentareTeilen
    -0.57
     Variability
    -0.54
    trät
    -0.51
     Adaptation
    -0.51
     اكتوبر
    -0.49
    getIntent
    -0.48
    zünd
    -0.48
    CHANGES
    -0.47
    dania
    -0.47
    POSITIVE LOGITS
    sing
    0.60
    memoized
    0.59
    HtmlAttribute
    0.54
    पया
    0.53
     HttpNotFound
    0.52
    titure
    0.52
    AccessorTable
    0.52
    انگلیسی
    0.51
     hammer
    0.50
    วา
    0.49
    Activations Density 0.004%

    No Known Activations