© 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. 5-CLT-HP
    7. 5151
    Prev
    Next
    INDEX
    Explanations

    which

    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
     habido
    -0.63
     held
    -0.58
     dilakukan
    -0.58
     exists
    -0.56
     runs
    -0.55
     occurred
    -0.54
     has
    -0.54
     run
    -0.53
    Fits
    -0.53
     occurs
    -0.52
    POSITIVE LOGITS
     to
    0.69
    EClass
    0.66
    GEBURTSDATUM
    0.59
     jspb
    0.57
     "..\..\..\
    0.56
     "..\..\
    0.53
    ptonshire
    0.52
    migrationBuilder
    0.52
    stdc
    0.52
    новниш
    0.52
    Activations Density 0.001%

    No Known Activations