© 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. 9374
    Prev
    Next
    INDEX
    Explanations

    is

    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
     onCancelled
    -0.53
    Diwedd
    -0.53
    Espèce
    -0.48
    Werke
    -0.47
    Identyfik
    -0.47
    AddRef
    -0.46
    ---|---|
    -0.46
    poptotic
    -0.46
    bleau
    -0.46
    ותו
    -0.44
    POSITIVE LOGITS
    
    0.76
     estekak
    0.68
    tvguidetime
    0.64
    awtextra
    0.63
    WindowConstants
    0.56
    født
    0.56
    Eloquent
    0.56
     promise
    0.54
     iconLine
    0.54
    AnchorStyles
    0.54
    Activations Density 0.189%

    No Known Activations