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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74191
    Prev
    Next
    INDEX
    Explanations

    Appreciation

    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
     againſt
    -0.94
     Jefus
    -0.91
     poffible
    -0.90
     Majefty
    -0.87
     reaſon
    -0.85
     ſame
    -0.85
     Diſ
    -0.85
     scolaires
    -0.83
     Theſe
    -0.83
     vermelhas
    -0.82
    POSITIVE LOGITS
     deeply
    0.55
     greatly
    0.51
     much
    0.47
     appreci
    0.45
     EXT
    0.43
     appreciate
    0.42
     extended
    0.42
     appre
    0.41
    postmedia
    0.40
     mucho
    0.40
    Activations Density 0.005%

    No Known Activations