© 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. 5-CLT-HP
    7. 92390
    Prev
    Next
    INDEX
    Explanations

    dashes and/or "post" usage

    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
    MLLoader
    -0.58
    uxxxx
    -0.55
    ündig
    -0.47
    >]
    -0.45
     незавершена
    -0.44
     doppelt
    -0.44
     JK
    -0.43
    goose
    -0.43
    AndEndTag
    -0.42
    รอ
    -0.41
    POSITIVE LOGITS
     (
    0.62
    KommentareTeilen
    0.56
     A
    0.56
    lators
    0.55
     وتسجيلات
    0.55
     Privacidade
    0.55
     Besitz
    0.50
    A
    0.50
    ptonshire
    0.50
    ampton
    0.50
    Activations Density 0.002%

    No Known Activations