© 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. 1-CLT-HP
    4. 45616
    Prev
    Next
    INDEX
    Explanations

    Published

    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
    Published
    -0.84
    Tembelea
    -0.66
     Published
    -0.65
    Images
    -0.58
    ıldığı
    -0.54
    Image
    -0.54
     autorytatywna
    -0.53
    bindParam
    -0.51
     adversaries
    -0.50
     Khe
    -0.50
    POSITIVE LOGITS
    LookAnd
    0.66
     }))
    0.54
     فريبيس
    0.54
    ochim
    0.51
     Note
    0.46
    Források
    0.45
    IVEREF
    0.45
    CORBA
    0.45
    '},
    
    0.45
     Recall
    0.44
    Activations Density 0.006%

    No Known Activations