© 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. 20-CLT-HP
    4. 75072
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    TagMode
    -0.76
     autorytatywna
    -0.74
    WithFormat
    -0.73
     OFDb
    -0.68
    ագրություններ
    -0.68
    Bibliograf
    -0.65
    IndentedString
    -0.65
    ArrowToggle
    -0.65
    Portail
    -0.63
     estekak
    -0.63
    POSITIVE LOGITS
    inheit
    0.39
    NameIn
    0.38
     lung
    0.37
     LIGHTS
    0.36
    RUnlock
    0.36
     eyebrow
    0.36
     index
    0.35
    dibles
    0.35
    namen
    0.35
     eyebrows
    0.35
    Activations Density 0.002%

    No Known Activations