© 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. 4-CLT-HP
    7. 4464
    Prev
    Next
    INDEX
    Explanations

    sometimes, infrequently

    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
     poffible
    -0.78
     وتسجيلات
    -0.74
     Jefus
    -0.73
    !*\
    -0.73
     leaſt
    -0.72
     autorytatywna
    -0.70
     laſt
    -0.67
     fometimes
    -0.66
    EDEFAULT
    -0.66
     juſ
    -0.66
    POSITIVE LOGITS
    heits
    0.65
    RenderAtEndOf
    0.58
    imar
    0.56
    
    0.56
     join
    0.56
     pop
    0.53
    فحة
    0.51
    anoke
    0.51
    sip
    0.50
    share
    0.50
    Activations Density 0.003%

    No Known Activations