© 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. 39885
    Prev
    Next
    INDEX
    Explanations

    wooden

    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
     steel
    -0.88
    steel
    -0.80
    SharedDtor
    -0.70
    ent
    -0.70
     convertView
    -0.66
    able
    -0.64
     cardboard
    -0.63
    تفصیلات
    -0.61
    culously
    -0.60
     Relatively
    -0.60
    POSITIVE LOGITS
    //
    0.51
    /*
    0.51
    /**
    0.47
    rungsseite
    0.46
    Roe
    0.45
    thalam
    0.45
    ibatis
    0.44
    #
    0.44
    
    0.44
     Everglades
    0.42
    Activations Density 0.308%

    No Known Activations