© 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. 601
    Prev
    Next
    INDEX
    Explanations

    on

    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
     "..\..\..\
    -0.56
     nî
    -0.47
     оно
    -0.47
    labelControl
    -0.46
    #
    -0.44
    dafx
    -0.43
    семь
    -0.43
    upassen
    -0.42
     mentales
    -0.42
     Geophysical
    -0.42
    POSITIVE LOGITS
    IComponent
    0.68
    webElementXpaths
    0.64
     the
    0.63
    Portail
    0.61
     you
    0.59
    RenderAtEndOf
    0.56
    parsedMessage
    0.55
    endu
    0.55
    MeasureSpec
    0.55
     nahilalakip
    0.54
    Activations Density 0.010%

    No Known Activations