© 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. 5-CLT-HP
    7. 92645
    Prev
    Next
    INDEX
    Explanations

    academic/technical subjects

    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
     Line
    -0.73
    Line
    -0.68
    rawDesc
    -0.62
     bancaire
    -0.60
    irchen
    -0.60
     Linie
    -0.60
    ValueStyle
    -0.60
     giustizia
    -0.60
     ainfi
    -0.59
    Шаг
    -0.58
    POSITIVE LOGITS
     area
    0.58
     مشين
    0.57
     matter
    0.57
     domain
    0.53
     AssemblyCulture
    0.51
    tvguidetime
    0.49
     mergeFrom
    0.49
     field
    0.47
    afone
    0.47
     material
    0.47
    Activations Density 0.001%

    No Known Activations