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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4
    Prev
    Next
    INDEX
    Explanations

    and

    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
    runApp
    -0.46
    BeginInit
    -0.46
    encodeWith
    -0.45
    @",
    -0.43
     gouver
    -0.42
    
    -0.41
    няка
    -0.41
    __':
    -0.41
    Américaine
    -0.41
    __':
    -0.40
    POSITIVE LOGITS
    帖最后由
    0.75
    存于互联网档案馆
    0.73
    homonymie
    0.65
     and
    0.64
    تقاوى
    0.60
    이고
    0.58
     <<<<<<<<<<<<<<
    0.57
     Wiktionnaire
    0.57
    TintMode
    0.56
    তথ্যসূত্র
    0.56
    Activations Density 0.046%

    No Known Activations