© 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. 72249
    Prev
    Next
    INDEX
    Explanations

    as

    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
    Autoritní
    -0.54
     CHRISTIAN
    -0.51
     religious
    -0.50
    :✨
    -0.50
    etCode
    -0.47
     ammi
    -0.47
     RELIG
    -0.46
     gospel
    -0.46
    etcode
    -0.45
     christian
    -0.45
    POSITIVE LOGITS
     He
    0.77
    #+#
    0.64
    UnusedPrivate
    0.63
     St
    0.60
    ce
    0.60
    WriteBarrier
    0.57
    UrlResolution
    0.57
    GOTREF
    0.57
    ISupport
    0.56
    occasione
    0.55
    Activations Density 0.000%

    No Known Activations