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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1165
    Prev
    Next
    INDEX
    Explanations

    now

    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
    enumi
    -0.51
     EdgeInsets
    -0.48
    Pranala
    -0.47
    tho
    -0.47
    inosi
    -0.46
     désolés
    -0.45
    pth
    -0.45
    pick
    -0.45
     pick
    -0.45
    Pick
    -0.45
    POSITIVE LOGITS
     Biôgrafia
    0.60
    Autoritní
    0.60
    TypedDataSet
    0.58
    üyada
    0.56
     Administrativna
    0.56
    matchCondition
    0.55
     Baillargeon
    0.54
    GEBURTSDATUM
    0.54
    AlterField
    0.53
     Roskov
    0.53
    Activations Density 0.001%

    No Known Activations