© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97529
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
     réguli
    -0.52
     berta
    -0.51
     posteriores
    -0.50
     supérieures
    -0.48
     réparer
    -0.48
    kezi
    -0.47
     âgées
    -0.46
     sopra
    -0.46
     européennes
    -0.46
     clô
    -0.45
    POSITIVE LOGITS
    s
    1.80
     itſelf
    1.05
     Monfieur
    1.04
     myſelf
    1.02
     Jefus
    0.96
    ship
    0.94
     Houſe
    0.94
     CreateTagHelper
    0.93
     Shakspeare
    0.92
     Efq
    0.92
    Activations Density 1.328%

    No Known Activations