© 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. 0-CLT-HP
    7. 1096
    Prev
    Next
    INDEX
    Explanations

    rict

    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
    ariums
    -0.84
    новништво
    -0.65
    vement
    -0.62
    monic
    -0.57
     Truman
    -0.54
    
    -0.54
     pixels
    -0.53
    obacterium
    -0.52
    Chham
    -0.52
    LookAnd
    -0.51
    POSITIVE LOGITS
    DockStyle
    0.56
    getResultList
    0.54
    stateProvider
    0.50
     secours
    0.49
    getDeclared
    0.48
     invloed
    0.48
     AspNetCore
    0.48
     hiver
    0.47
    ilhas
    0.45
    ו
    0.45
    Activations Density 0.237%

    No Known Activations