© 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. 0-CLT-HP
    7. 41936
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     poffible
    -0.74
     uſed
    -0.73
     protested
    -0.71
     poffe
    -0.69
     myſelf
    -0.69
     leſs
    -0.65
     pleaf
    -0.64
     promised
    -0.63
     ſaid
    -0.63
     pleaſure
    -0.63
    POSITIVE LOGITS
    ing
    0.82
    er
    0.59
    ure
    0.57
    %
    0.56
     a
    0.55
    esis
    0.55
    ']->
    0.55
     an
    0.54
     Процитовано
    0.54
    Legături
    0.53
    Activations Density 0.201%

    No Known Activations