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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12837
    Prev
    Next
    INDEX
    Explanations

    independence

    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
    Espèce
    -0.81
     Theſe
    -0.70
     Monfieur
    -0.69
     viſ
    -0.69
    ]?.
    -0.66
     Reſ
    -0.66
     purpoſe
    -0.65
    chaun
    -0.65
     itſelf
    -0.64
     tartalomajánló
    -0.64
    POSITIVE LOGITS
     فريبيس
    0.57
    erover
    0.49
     Vikipedi
    0.47
     of
    0.45
     EdgeInsets
    0.43
    CloseOperation
    0.43
    蚊
    0.43
    my
    0.43
     Ar
    0.42
     er
    0.42
    Activations Density 0.010%

    No Known Activations