© 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. 45085
    Prev
    Next
    INDEX
    Explanations

    currently

    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
     currently
    -1.60
    currently
    -1.35
     Currently
    -1.30
     actuellement
    -1.29
    Currently
    -1.27
     actualmente
    -1.22
     attualmente
    -1.19
     atualmente
    -1.17
     current
    -1.13
     derzeit
    -1.12
    POSITIVE LOGITS
    bewerken
    0.69
    aarrggbb
    0.67
    oredCriteria
    0.66
    évaluateur
    0.63
    +#+#
    0.63
     "..\..\..\
    0.62
     مشين
    0.59
    Diweddarwch
    0.57
     Италијани
    0.57
    argout
    0.56
    Activations Density 0.123%

    No Known Activations