© 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. 94911
    Prev
    Next
    INDEX
    Explanations

    options

    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
    tips
    -0.58
     فرو
    -0.57
    为止
    -0.53
    se
    -0.53
     Director
    -0.53
    Tips
    -0.51
     Answers
    -0.51
    ks
    -0.50
    come
    -0.50
    alk
    -0.50
    POSITIVE LOGITS
    MigrationBuilder
    0.76
    ExtendWith
    0.69
    észetes
    0.66
     gawas
    0.65
    seamnă
    0.64
     EnglishChoose
    0.63
     مشين
    0.63
    Atsauces
    0.62
    цездатний
    0.62
    ValueStyle
    0.60
    Activations Density 0.122%

    No Known Activations