© 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. 38776
    Prev
    Next
    INDEX
    Explanations

    language structure

    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
     ſeveral
    -0.74
    Tikang
    -0.73
    ]]
    
    -0.65
    Configurer
    -0.60
     beſt
    -0.60
     uVar
    -0.60
     ActionResult
    -0.60
    figur
    -0.59
    MediaStore
    -0.59
    NESS
    -0.58
    POSITIVE LOGITS
    Personensuche
    0.70
     الرياضيه
    0.63
     CreateTagHelper
    0.62
    fjspx
    0.61
     disambiguazione
    0.58
    ftagPool
    0.54
    InjectAttribute
    0.53
     تضيفلها
    0.53
    ConstraintMaker
    0.53
     Italijani
    0.52
    Activations Density 0.015%

    No Known Activations