© 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. 15546
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    <bos>
    -0.71
    InstrumentedTest
    -0.66
    ValueStyle
    -0.64
    kháu
    -0.64
     Tuk
    -0.63
    ſelf
    -0.60
     Dutton
    -0.59
    UserScript
    -0.58
    Geplaatst
    -0.57
    NameInMap
    -0.57
    POSITIVE LOGITS
     privados
    0.60
     mecán
    0.60
     stället
    0.58
     tämä
    0.57
     scoperta
    0.56
     illustrazione
    0.54
     prossima
    0.54
     emberek
    0.54
     scolaires
    0.53
    ISTRY
    0.53
    Activations Density 0.027%

    No Known Activations