© 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. 72117
    Prev
    Next
    INDEX
    Explanations

    /

    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
     R
    -0.66
    R
    -0.59
     rep
    -0.53
    rep
    -0.52
    Rep
    -0.52
     kasarigan
    -0.50
    man
    -0.49
     Rep
    -0.49
     man
    -0.48
    eaus
    -0.47
    POSITIVE LOGITS
     purpoſe
    0.65
     Theſe
    0.63
     myſelf
    0.62
    ValueStyle
    0.62
    makeConstraints
    0.61
     Monfieur
    0.60
     feroit
    0.60
    elemField
    0.60
     ainfi
    0.59
     auroit
    0.59
    Activations Density 0.000%

    No Known Activations