Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73887
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · 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
    تقاوى
    -0.55
    Portale
    -0.44
     كومونز
    -0.43
     groom
    -0.43
    Erreferentziak
    -0.42
     junit
    -0.40
     beru
    -0.39
    ってみて
    -0.39
     Vino
    -0.39
     apt
    -0.38
    POSITIVE LOGITS
    8
    0.73
    AddHtmlAttribute
    0.69
    7
    0.67
    9
    0.62
    6
    0.60
    étrie
    0.60
    хьтан
    0.59
     Eighth
    0.57
     poveznice
    0.56
    zzlies
    0.54
    Activations Density 0.002%

    No Known Activations