© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90443
    Prev
    Next
    INDEX
    Explanations

    programming, names

    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
    endregion
    -0.71
    Pres
    -0.66
     Hab
    -0.63
    pres
    -0.62
    apat
    -0.60
     thủ
    -0.60
    Hab
    -0.59
    enumi
    -0.56
     hab
    -0.56
     Pres
    -0.53
    POSITIVE LOGITS
    TargetException
    0.63
    URLException
    0.59
     photolibrary
    0.56
     Publicar
    0.55
     religieuses
    0.55
    Története
    0.54
    PreferredItem
    0.53
    każ
    0.53
    ︎
    0.53
    beiros
    0.52
    Activations Density 0.230%

    No Known Activations