© 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. 91686
    Prev
    Next
    INDEX
    Explanations

    Numbers and comparisons

    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
    optera
    -0.52
    endif
    -0.44
    πον
    -0.42
    atine
    -0.42
    szönöm
    -0.41
    vas
    -0.41
    ุง
    -0.41
     dessus
    -0.41
     relative
    -0.41
    Math
    -0.41
    POSITIVE LOGITS
     Мексичка
    0.89
    abestanden
    0.82
     invokingState
    0.80
     resourceCulture
    0.79
     Италијани
    0.79
     незавершена
    0.76
     typelib
    0.75
     насељу
    0.73
    enumii
    0.73
    encodeWith
    0.71
    Activations Density 0.002%

    No Known Activations