© 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. 76990
    Prev
    Next
    INDEX
    Explanations

    Naming or identifying

    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
     réguli
    -0.69
     scolaires
    -0.65
     élevées
    -0.63
     complètes
    -0.63
     varandra
    -0.62
     öppna
    -0.60
     abiertas
    -0.60
     skydd
    -0.59
     ouvertes
    -0.58
     définiti
    -0.57
    POSITIVE LOGITS
     call
    0.97
     consider
    0.82
     refer
    0.80
    enumi
    0.78
     Called
    0.74
     calls
    0.71
     فريبيس
    0.69
     identify
    0.68
     know
    0.68
     suppose
    0.65
    Activations Density 0.000%

    No Known Activations