© 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. 0-CLT-HP
    7. 94904
    Prev
    Next
    INDEX
    Explanations

    failure

    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
     fraction
    -1.00
     proportion
    -0.86
    proportion
    -0.85
     Failure
    -0.79
     failure
    -0.79
     Fraction
    -0.77
    portion
    -0.75
     portion
    -0.73
    writeFieldEnd
    -0.73
     Proportion
    -0.70
    POSITIVE LOGITS
    ing
    1.07
    ed
    0.91
    a
    0.76
    e
    0.74
    ated
    0.68
    ING
    0.66
    y
    0.65
    AndEndTag
    0.64
    i
    0.64
    ic
    0.63
    Activations Density 0.056%

    No Known Activations