© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76206
    Prev
    Next
    INDEX
    Explanations

    Number five

    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
     chuy
    -0.49
    āya
    -0.47
    pog
    -0.47
     problems
    -0.46
     знак
    -0.45
     transférez
    -0.45
     odp
    -0.44
    URLException
    -0.44
    !*\
    -0.44
    VYMaps
    -0.43
    POSITIVE LOGITS
     fifth
    0.63
     fifteenth
    0.59
     Fifth
    0.58
     nahilalakip
    0.58
    Fifteen
    0.56
    十五
    0.54
     FIFTH
    0.54
    Fifth
    0.54
     Fifteen
    0.54
     Five
    0.53
    Activations Density 0.000%

    No Known Activations