© 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. 42453
    Prev
    Next
    INDEX
    Explanations

    cycle

    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
    WriteTagHelper
    -0.53
     travailleurs
    -0.52
     neige
    -0.51
    MLLoader
    -0.50
    paciente
    -0.50
    lotl
    -0.50
    重
    -0.50
    archiw
    -0.49
    rdoba
    -0.48
     старости
    -0.48
    POSITIVE LOGITS
    <bos>
    0.56
    يميديا
    0.56
     PyLong
    0.54
    ViewFeatures
    0.53
     بلکه
    0.52
     ")");
    0.51
    Geplaatst
    0.49
    diğini
    0.48
     _("
    0.48
    InvalidProtocol
    0.47
    Activations Density 0.288%

    No Known Activations