© 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. 14396
    Prev
    Next
    INDEX
    Explanations

    "there" contexts

    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
     HasFactory
    -0.66
    AndEndTag
    -0.65
    ggiamento
    -0.63
     distanciation
    -0.61
    ="#"><
    -0.60
    uttavia
    -0.56
    󠁮
    -0.56
    ptonshire
    -0.56
    togram
    -0.55
    tily
    -0.54
    POSITIVE LOGITS
    webElementXpaths
    0.50
    ModelBuilder
    0.47
    MigrationBuilder
    0.44
    icose
    0.42
     ExecuteAsync
    0.41
    imageshack
    0.41
    world
    0.40
    Ārējās
    0.40
    Архівовано
    0.40
    fillType
    0.40
    Activations Density 0.007%

    No Known Activations