© 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. 5-CLT-HP
    7. 5864
    Prev
    Next
    INDEX
    Explanations

    [

    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
     doInBackground
    -0.48
    Lähteet
    -0.47
     isn
    -0.46
    ,'
    -0.46
     дописавши
    -0.45
    ">//
    -0.44
    guet
    -0.42
     مشين
    -0.41
    Điện
    -0.41
    Роди
    -0.41
    POSITIVE LOGITS
     NSError
    0.65
     MainAxisSize
    0.62
    Архівовано
    0.59
    endpush
    0.57
     Partagez
    0.57
     holotype
    0.57
     hydrauli
    0.55
     tslint
    0.54
     Anm
    0.54
    PreferredItem
    0.54
    Activations Density 0.039%

    No Known Activations