© 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. 94259
    Prev
    Next
    INDEX
    Explanations

    Gar

    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
     source
    -1.01
     gar
    -0.98
     Gar
    -0.82
     Source
    -0.78
    gar
    -0.73
     src
    -0.69
     sources
    -0.69
    source
    -0.69
    GAR
    -0.64
     SOURCE
    -0.63
    POSITIVE LOGITS
     avoient
    0.98
     étoient
    0.86
     fermés
    0.85
     فريبيس
    0.85
     médicaux
    0.85
     feroit
    0.83
     rempliss
    0.81
     automatiques
    0.81
     traditionnels
    0.80
     auroit
    0.80
    Activations Density 0.153%

    No Known Activations