© 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. 4-CLT-HP
    7. 787
    Prev
    Next
    INDEX
    Explanations

    prefixes hyper and hypo

    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
     autorytatywna
    -0.60
     nawr
    -0.59
    DockStyle
    -0.57
     consulté
    -0.57
    osoba
    -0.54
    ́s
    -0.53
    !*\
    -0.53
     Administrativna
    -0.52
    клопе
    -0.52
     scattata
    -0.52
    POSITIVE LOGITS
    TemporalType
    0.53
    ThroughAttribute
    0.51
     ter
    0.47
    ylim
    0.47
    olverine
    0.46
    GraphicsUnit
    0.46
    AlterField
    0.46
     laps
    0.46
    thermia
    0.46
    tim
    0.45
    Activations Density 0.000%

    No Known Activations