© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41346
    Prev
    Next
    INDEX
    Explanations

    limus

    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
    oredCriteria
    -0.82
     colorés
    -0.79
    ArrowToggle
    -0.77
    GraphicsUnit
    -0.77
     médié
    -0.75
     nationaux
    -0.72
     stället
    -0.72
     sauvages
    -0.72
    Vidite
    -0.70
     avoient
    -0.70
    POSITIVE LOGITS
    i
    0.76
    e
    0.75
    er
    0.70
    z
    0.61
    ity
    0.60
    a
    0.60
    itya
    0.55
    ه
    0.54
    es
    0.52
    iak
    0.51
    Activations Density 0.064%

    No Known Activations