© 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. 5-CLT-HP
    7. 93510
    Prev
    Next
    INDEX
    Explanations

    4

    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
     оригіналу
    -0.63
     mécanisme
    -0.60
    ceps
    -0.57
    álen
    -0.57
     équilibr
    -0.56
    BindView
    -0.55
     ácido
    -0.54
     Bonner
    -0.53
    URIComponent
    -0.53
    ValueStyle
    -0.53
    POSITIVE LOGITS
    مراجع
    0.55
    Portail
    0.54
    __*/
    0.48
    TintMode
    0.46
    hnia
    0.46
    IVEREF
    0.43
     Svar
    0.43
    Svar
    0.42
     demikian
    0.40
    AnchorTagHelper
    0.40
    Activations Density 0.000%

    No Known Activations