© 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. 4-CLT-HP
    7. 75
    Prev
    Next
    INDEX
    Explanations

    people

    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
     of
    -0.90
    (
    -0.56
    of
    -0.56
    }{*}{
    -0.52
     nors
    -0.49
    ries
    -0.49
    tof
    -0.49
    thun
    -0.48
    biór
    -0.47
    (\
    -0.45
    POSITIVE LOGITS
    SPJ
    0.70
    rungsseite
    0.61
    SerializedName
    0.59
    multer
    0.58
    '])->
    0.58
    clientY
    0.56
    AddHtmlAttribute
    0.56
    reactstrap
    0.55
    SharedCtor
    0.55
    AddTagHelper
    0.54
    Activations Density 0.001%

    No Known Activations