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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 105
    Prev
    Next
    INDEX
    Explanations

    References to people

    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
     élé
    -0.49
     ritrov
    -0.47
     kiş
    -0.47
    зна
    -0.43
    ötz
    -0.43
    complexType
    -0.41
     spécifique
    -0.40
    tling
    -0.40
     giudi
    -0.40
    dee
    -0.40
    POSITIVE LOGITS
    httphttps
    0.71
    Rhestr
    0.69
     wish
    0.68
     distribute
    0.67
     propose
    0.67
    MLLoader
    0.66
     surla
    0.66
    σιμοποι
    0.65
     preside
    0.65
    dflare
    0.64
    Activations Density 0.010%

    No Known Activations