© 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. 12101
    Prev
    Next
    INDEX
    Explanations

    with

    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
    تقاوى
    -0.83
     beginnetje
    -0.69
     kaarangay
    -0.62
    mobileqq
    -0.62
     gyhoeddwyd
    -0.59
    StreetMap
    -0.56
     незавершена
    -0.54
     autorytatywna
    -0.54
    حياته
    -0.53
    CopyWith
    -0.53
    POSITIVE LOGITS
     and
    0.68
    execSQL
    0.66
     setOpen
    0.59
    帖最后由
    0.57
     acrylique
    0.56
    DispatchToProps
    0.55
    sium
    0.55
    ChildScrollView
    0.55
     arXiv
    0.54
    ffindor
    0.54
    Activations Density 0.066%

    No Known Activations