© 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. 14986
    Prev
    Next
    INDEX
    Explanations

    Code licenses

    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
     Pyle
    -0.51
     huiles
    -0.50
    imentel
    -0.48
     céramique
    -0.47
    Nio
    -0.46
    EDI
    -0.45
    poni
    -0.45
    setViewport
    -0.44
    meln
    -0.44
     cotone
    -0.43
    POSITIVE LOGITS
     NSCoder
    0.71
    AndEndTag
    0.69
    tagHelperRunner
    0.68
    protoc
    0.59
     JSTOR
    0.59
    ThroughAttribute
    0.57
    PageRoute
    0.55
     Frog
    0.55
    @[+][
    0.54
    LookAnd
    0.54
    Activations Density 0.035%

    No Known Activations