© 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. 42191
    Prev
    Next
    INDEX
    Explanations

    giving examples

    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
     sonriendo
    -0.69
     oreilles
    -0.68
     netting
    -0.64
     carreaux
    -0.63
     stappen
    -0.63
     panneaux
    -0.63
     sibuk
    -0.62
    addPreferredGap
    -0.61
     reír
    -0.61
     réussite
    -0.61
    POSITIVE LOGITS
    iest
    0.68
    ed
    0.66
    ier
    0.61
    ized
    0.58
    ize
    0.58
    izes
    0.57
    ingly
    0.57
    ion
    0.54
    ance
    0.54
    cer
    0.53
    Activations Density 1.613%

    No Known Activations