© 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. 20-CLT-HP
    7. 76982
    Prev
    Next
    INDEX
    Explanations

    Code/foreign words

    np_max-act-logits · 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
    AnchorStyles
    -0.59
     Sog
    -0.58
     समीक्षाओं
    -0.57
    IsInitialized
    -0.57
    gms
    -0.57
     Nid
    -0.56
     gts
    -0.56
     Bes
    -0.56
     Bey
    -0.56
    seid
    -0.56
    POSITIVE LOGITS
    |}{}
    0.50
    følge
    0.46
     eléctricas
    0.45
     {{{
    0.44
    TTE
    0.43
     PEP
    0.42
    umahan
    0.41
    tanleria
    0.41
     Zweiten
    0.40
     LOU
    0.39
    Activations Density 0.000%

    No Known Activations