© 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. 5-CLT-HP
    7. 97820
    Prev
    Next
    INDEX
    Explanations

    datetimes

    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
     bénévoles
    -0.65
     prêtres
    -0.63
     vérit
    -0.61
     regulares
    -0.60
     AssemblyCulture
    -0.59
     disponibilité
    -0.59
     lèvres
    -0.58
     urbaine
    -0.58
     älskar
    -0.56
     nuages
    -0.56
    POSITIVE LOGITS
    AutoField
    0.53
    Sucesor
    0.53
    Viited
    0.51
    XMLSchema
    0.49
    %)$
    0.48
    ArgsConstructor
    0.48
     محفوظة
    0.47
    msgSender
    0.46
     quarter
    0.46
    Rüyada
    0.45
    Activations Density 0.011%

    No Known Activations