© 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. 9635
    Prev
    Next
    INDEX
    Explanations

    do

    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
    ers
    -0.49
    wendungen
    -0.47
    aux
    -0.46
    ier
    -0.43
    ings
    -0.43
    udu
    -0.42
    lings
    -0.40
    ous
    -0.40
    lab
    -0.40
    er
    -0.39
    POSITIVE LOGITS
     MainAxisSize
    0.94
     estekak
    0.81
    ChildScrollView
    0.76
    webElementXpaths
    0.76
    ConstraintMaker
    0.73
    Jereo
    0.73
    fjspx
    0.70
    GLenum
    0.69
     }}"></
    0.68
    writeFieldEnd
    0.68
    Activations Density 0.054%

    No Known Activations