© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96704
    Prev
    Next
    INDEX
    Explanations

    Capitalized letter groups

    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
    WebElementEntity
    -0.75
    onee
    -0.53
    celles
    -0.52
    elemField
    -0.50
    eeq
    -0.47
    expiresIn
    -0.47
     satunya
    -0.47
    BufferException
    -0.46
    তথ্যসূত্র
    -0.46
     apalagi
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.85
     over
    0.78
    Становништво
    0.59
    visor
    0.56
    idoscope
    0.50
     vineyard
    0.48
    dération
    0.48
    vignon
    0.47
     Estuary
    0.47
     backyard
    0.47
    Activations Density 0.005%

    No Known Activations