© 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. 5-CLT-HP
    4. 96282
    Prev
    Next
    INDEX
    Explanations

    world

    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
    <?,
    -0.62
    LookAnd
    -0.58
    usermodel
    -0.54
    TRIBUN
    -0.52
    iplin
    -0.49
    lotl
    -0.47
    cesor
    -0.47
    '>
    
    -0.47
    startActivity
    -0.47
    taxis
    -0.47
    POSITIVE LOGITS
    views
    0.65
     esternos
    0.63
    view
    0.63
     view
    0.61
    owns
    0.56
     resourceCulture
    0.54
    GOTREF
    0.54
     MenuView
    0.52
    matchCondition
    0.52
     getView
    0.52
    Activations Density 0.000%

    No Known Activations