© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45399
    Prev
    Next
    INDEX
    Explanations

    attributes

    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
    θρώ
    -0.73
     Theſe
    -0.68
     EnglishChoose
    -0.67
    ]='\
    -0.67
    )"),
    -0.66
     myſelf
    -0.65
     itſelf
    -0.64
    )");
    
    -0.63
    ênis
    -0.62
     }}"></
    -0.62
    POSITIVE LOGITS
    .
    0.67
    ,
    0.63
    RectangleBorder
    0.59
    stra
    0.54
     useRef
    0.52
    pri
    0.51
    /***/
    0.51
    ad
    0.49
    kol
    0.48
    nd
    0.48
    Activations Density 0.607%

    No Known Activations