© 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. 5821
    Prev
    Next
    INDEX
    Explanations

    dash

    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
    TypedDataSet
    -0.93
    principalColumn
    -0.71
    RectangleBorder
    -0.63
    TestingModule
    -0.59
    
    -0.59
    afficheront
    -0.57
    %");
    -0.57
    ołnier
    -0.55
    Hochspringen
    -0.55
    MENAFN
    -0.52
    POSITIVE LOGITS
     consistently
    0.54
    rawDesc
    0.52
    strconv
    0.49
     contin
    0.49
     Consist
    0.48
     старости
    0.47
     multiple
    0.47
     routinely
    0.46
     faithfully
    0.46
    ագրություններ
    0.45
    Activations Density 0.001%

    No Known Activations