© 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. 10237
    Prev
    Next
    INDEX
    Explanations

    attitudes

    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
    يانة
    -0.57
    titudes
    -0.54
    RegressionTest
    -0.51
    θε
    -0.50
    luss
    -0.50
    WebElementEntity
    -0.48
    GIN
    -0.48
    box
    -0.48
    __':
    -0.46
    eth
    -0.46
    POSITIVE LOGITS
     المعيارى
    0.60
     Whal
    0.54
    anty
    0.52
    ally
    0.49
    
    0.49
    otras
    0.48
     hạng
    0.48
    lgari
    0.48
     halter
    0.47
    entile
    0.47
    Activations Density 0.008%

    No Known Activations