© 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. 20-CLT-HP
    7. 77523
    Prev
    Next
    INDEX
    Explanations

    ary

    np_max-act-logits · 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
    StreetMap
    -0.60
     désolés
    -0.54
     fusca
    -0.54
    nesto
    -0.53
     Aufbau
    -0.51
    ensitive
    -0.51
    IsContent
    -0.51
     strictest
    -0.51
     switching
    -0.50
    importanza
    -0.50
    POSITIVE LOGITS
    aries
    0.73
    ary
    0.68
    ARY
    0.58
    äj
    0.56
    __':
    0.55
    ARIES
    0.49
    QMetaType
    0.48
    HomeAsUpEnabled
    0.47
    TemporalType
    0.47
    __':
    0.47
    Activations Density 0.002%

    No Known Activations