© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15333
    Prev
    Next
    INDEX
    Explanations

    colon

    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
     Wikimedijinoj
    -0.67
    kháu
    -0.67
    ,
    -0.61
     NUKAT
    -0.59
    "
    -0.58
     חיצוניים
    -0.57
     Normdatei
    -0.56
    .")
    -0.55
    AddTagHelper
    -0.54
    awtextra
    -0.54
    POSITIVE LOGITS
     myſelf
    0.64
    ially
    0.62
     a
    0.61
     purpoſe
    0.60
     let
    0.57
    ↵
    0.57
     ſay
    0.56
     reaſon
    0.55
     raiſ
    0.54
     ſaid
    0.53
    Activations Density 0.075%

    No Known Activations