© 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. 20-CLT-HP
    7. 77072
    Prev
    Next
    INDEX
    Explanations

    specific words

    np_max-act-logits · 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
    ENED
    -0.52
    HN
    -0.51
    encodeWith
    -0.50
    エン
    -0.50
    varu
    -0.49
    gento
    -0.48
    JN
    -0.48
     Noor
    -0.48
    eln
    -0.48
     NN
    -0.48
    POSITIVE LOGITS
    jsii
    0.56
    ksi
    0.54
     ksi
    0.53
     ki
    0.53
    rungsseite
    0.50
    Slik
    0.49
    ksis
    0.49
    KSI
    0.48
    AddTagHelper
    0.46
     wij
    0.46
    Activations Density 0.000%

    No Known Activations