© 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. 43329
    Prev
    Next
    INDEX
    Explanations

    legal and medical topics

    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
    MigrationBuilder
    -0.59
     linkovi
    -0.56
    tvguidetime
    -0.55
    iq
    -0.54
    Demografie
    -0.52
     Roskov
    -0.52
    iks
    -0.52
     sus
    -0.51
    expandindo
    -0.51
    crimes
    -0.51
    POSITIVE LOGITS
    ness
    0.64
    出版年
    0.63
    paravant
    0.58
    DispatchToProps
    0.56
    ly
    0.56
    piecze
    0.55
    millan
    0.54
     AssemblyTitle
    0.54
    mismo
    0.53
    swell
    0.53
    Activations Density 0.195%

    No Known Activations