© 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. 4-CLT-HP
    7. 64
    Prev
    Next
    INDEX
    Explanations

    datelines

    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
     فريبيس
    -0.69
    kloped
    -0.68
    AddTagHelper
    -0.65
     mourut
    -0.60
    SizeF
    -0.58
    HtmlAttribute
    -0.57
    harapkan
    -0.56
     vägen
    -0.55
     exemplaires
    -0.54
    styleType
    -0.54
    POSITIVE LOGITS
    Vapour
    0.59
    Trav
    0.50
     vapour
    0.50
    favourable
    0.49
    labour
    0.49
     standardised
    0.49
     diarrhoea
    0.49
     Vapour
    0.48
     flavours
    0.48
     neighbourhood
    0.47
    Activations Density 0.003%

    No Known Activations