© 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. 20-CLT-HP
    7. 72284
    Prev
    Next
    INDEX
    Explanations

    ment

    np_max-act-logits · 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
    esgue
    -0.56
    velocityY
    -0.50
    गु
    -0.47
    álva
    -0.47
    hdessä
    -0.47
    zyb
    -0.47
    ciana
    -0.47
     Schia
    -0.46
    poa
    -0.46
     libras
    -0.46
    POSITIVE LOGITS
    ment
    2.08
    MENT
    1.55
    ments
    1.52
    ement
    1.41
    EMENT
    1.30
    mento
    1.20
    lement
    1.19
    ament
    1.16
     ment
    1.14
    iment
    1.13
    Activations Density 0.007%

    No Known Activations