© 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. 1-CLT-HP
    7. 15856
    Prev
    Next
    INDEX
    Explanations

    academic texts and collections

    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
    Personendaten
    -0.67
     resourceCulture
    -0.57
    <bos>
    -0.56
    endphp
    -0.55
    awtextra
    -0.54
    expandindo
    -0.52
     EconPapers
    -0.52
     hesitate
    -0.48
    posia
    -0.48
    erol
    -0.47
    POSITIVE LOGITS
    usermodel
    0.54
    konomi
    0.52
    gól
    0.50
    uldade
    0.49
    cyklo
    0.48
    żesz
    0.46
    otyp
    0.46
     Baillargeon
    0.46
    onomic
    0.44
    toupper
    0.44
    Activations Density 0.003%

    No Known Activations