© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 15510
    Prev
    Next
    INDEX
    Explanations

    host

    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
     normaux
    -0.72
     pouvoit
    -0.66
     fournis
    -0.66
     tendenza
    -0.66
     complètes
    -0.66
     humaines
    -0.65
     réguli
    -0.64
     quelcon
    -0.63
     élas
    -0.63
     étoit
    -0.63
    POSITIVE LOGITS
    RenderAtEndOf
    0.56
     crop
    0.51
     sto
    0.48
    XtraReports
    0.48
    例句
    0.48
    Vorlage
    0.45
    __*/
    0.45
     food
    0.43
     weed
    0.43
    ində
    0.42
    Activations Density 0.015%

    No Known Activations