© 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. 1-CLT-HP
    7. 10200
    Prev
    Next
    INDEX
    Explanations

    Suf

    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
     gratuites
    -0.52
     automatiques
    -0.52
    FAQ
    -0.50
     latein
    -0.50
    OrBuilder
    -0.50
     extérieures
    -0.48
     Autó
    -0.47
     pères
    -0.46
    oksi
    -0.46
     hivyo
    -0.46
    POSITIVE LOGITS
    adpleegd
    0.74
     متعلقه
    0.68
     MainAxisSize
    0.65
    PreferredItem
    0.63
    IonicModule
    0.57
    المكان
    0.55
    Fordítás
    0.55
    OUS
    0.55
    ništvo
    0.54
     createSlice
    0.54
    Activations Density 0.011%

    No Known Activations