© 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. 94541
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    est
    -0.57
    stra
    -0.48
     marito
    -0.48
    </b>
    -0.47
     capacidade
    -0.46
    <h1>
    -0.45
     γρα
    -0.45
     idéia
    -0.45
     beste
    -0.44
    サン
    -0.44
    POSITIVE LOGITS
     estekak
    0.79
     auffi
    0.78
     Савезне
    0.78
     Efq
    0.78
     myſelf
    0.78
     keV
    0.75
     adjournment
    0.75
    iastes
    0.71
     >=",
    0.71
    хьтан
    0.70
    Activations Density 1.228%

    No Known Activations