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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11995
    Prev
    Next
    INDEX
    Explanations

    code, links, data formatting

    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
    ché
    -1.09
     cropped
    -0.92
    cropped
    -0.66
    chés
    -0.52
    chè
    -0.52
     itſelf
    -0.49
     FetchType
    -0.48
    usermodel
    -0.47
    formKey
    -0.47
     Xer
    -0.47
    POSITIVE LOGITS
    +#+#
    0.79
    RegistryLite
    0.69
     Goodrich
    0.62
    adz
    0.58
     wet
    0.58
     Meksiku
    0.56
     للاسماء
    0.55
    fromnode
    0.54
    ValueStyle
    0.53
    dehydes
    0.52
    Activations Density 0.004%

    No Known Activations