© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45364
    Prev
    Next
    INDEX
    Explanations

    research papers/technical documentation

    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
     idolatry
    -0.97
    findpost
    -0.63
     Audiodateien
    -0.63
     Diſ
    -0.56
    msa
    -0.55
     Eſ
    -0.55
     superiori
    -0.54
    SEGUIR
    -0.52
    NOPQRST
    -0.52
    κος
    -0.51
    POSITIVE LOGITS
     nahilalakip
    0.60
     Muda
    0.55
     ग्राहक
    0.54
    astify
    0.53
    ArrowToggle
    0.52
    tagHelperRunner
    0.51
    lasma
    0.51
    prüche
    0.50
    abus
    0.50
    zzleHttp
    0.50
    Activations Density 1.593%

    No Known Activations