© 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. 4-CLT-HP
    4. 2764
    Prev
    Next
    INDEX
    Explanations

    as by

    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
    κε
    -0.52
     vez
    -0.52
     Alkali
    -0.50
     verbs
    -0.50
    Kalb
    -0.49
     bonfire
    -0.49
     itſelf
    -0.48
     Reuben
    -0.48
     Verbs
    -0.47
    spreis
    -0.47
    POSITIVE LOGITS
    :
    0.69
     the
    0.68
    DoubleQuotes
    0.66
    RegistryLite
    0.59
    expandindo
    0.57
     CanadaChoose
    0.56
    ,
    0.54
    DockStyle
    0.54
    ($__
    0.53
     but
    0.52
    Activations Density 0.002%

    No Known Activations