© 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. 1-CLT-HP
    7. 11424
    Prev
    Next
    INDEX
    Explanations

    a

    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
     Wikimedijinoj
    -0.73
     wikipagina
    -0.71
     resourceCulture
    -0.70
     '{@
    -0.68
     flesta
    -0.68
    protoimpl
    -0.67
    èdia
    -0.67
    mereka
    -0.67
     <>",
    -0.66
     Estatal
    -0.66
    POSITIVE LOGITS
     were
    0.55
     well
    0.54
     are
    0.54
     totul
    0.50
     long
    0.49
    .
    0.49
    '
    0.48
     happen
    0.48
    ).
    0.46
     have
    0.45
    Activations Density 0.046%

    No Known Activations