© 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. 42922
    Prev
    Next
    INDEX
    Explanations

    ({

    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
    IntoConstraints
    -0.82
    GEBURTSDATUM
    -0.81
    numerusform
    -0.63
    Билгалдахарш
    -0.62
    oa̍t
    -0.58
     BoxDecoration
    -0.57
    aarrggbb
    -0.57
    SPATH
    -0.55
    ябре
    -0.54
    Leif
    -0.54
    POSITIVE LOGITS
    LookAnd
    0.68
     urbanos
    0.57
    IUrlHelper
    0.55
    colgroup
    0.54
    AsUp
    0.53
     urbanas
    0.52
    mability
    0.51
    ttä
    0.50
    barkeit
    0.48
    ization
    0.48
    Activations Density 0.833%

    No Known Activations