© 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. 976
    Prev
    Next
    INDEX
    Explanations

    code/formal documents

    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
    +:+
    -0.60
     lengte
    -0.59
    ėmis
    -0.57
    mería
    -0.57
     تانيه
    -0.56
    aries
    -0.56
    Ӏ
    -0.56
    LookAnd
    -0.54
    érape
    -0.54
     gedrag
    -0.54
    POSITIVE LOGITS
    mybatisplus
    0.56
     onPostExecute
    0.55
    CloseOperation
    0.54
     segi
    0.53
    enumi
    0.52
     snippetHide
    0.50
    AccessorTable
    0.49
    PreAuthorize
    0.48
    StackNavigator
    0.48
     Stopwatch
    0.48
    Activations Density 1.754%

    No Known Activations