© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90950
    Prev
    Next
    INDEX
    Explanations

    Descriptive texts and studies

    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
     matters
    -0.93
    matters
    -0.75
    ISO
    -0.70
     ISO
    -0.66
     autorytatywna
    -0.64
     الحره
    -0.63
     MATTERS
    -0.59
     Matters
    -0.58
    inform
    -0.57
     conductor
    -0.56
    POSITIVE LOGITS
     DBNull
    0.60
    ModelSerializer
    0.59
    TagHelpers
    0.59
     itſelf
    0.58
    inars
    0.55
    ietal
    0.55
    NewGuid
    0.54
    scryfall
    0.54
     againſt
    0.53
     demurrer
    0.53
    Activations Density 1.610%

    No Known Activations