© 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. 0-CLT-HP
    7. 94057
    Prev
    Next
    INDEX
    Explanations

    Computing and organizations

    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
    e
    -0.84
     Unit
    -0.82
    Unit
    -0.80
    o
    -0.66
    a
    -0.66
    y
    -0.66
    er
    -0.63
    ه
    -0.61
    ing
    -0.58
    en
    -0.56
    POSITIVE LOGITS
     Efq
    0.82
     ainfi
    0.75
    fromCharCode
    0.73
    Tarifs
    0.71
    ifrance
    0.71
    berdayakan
    0.70
    amaño
    0.69
     zelve
    0.69
     €)
    0.69
     plufieurs
    0.69
    Activations Density 0.300%

    No Known Activations