© 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. 0-CLT-HP
    4. 97290
    Prev
    Next
    INDEX
    Explanations

    online articles and blogs

    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
     Мексичка
    -0.79
    LookAnd
    -0.73
    OGND
    -0.71
    uxxxx
    -0.71
    parsedMessage
    -0.70
    __':
    -0.66
    MigrationBuilder
    -0.66
    '])->
    -0.64
    ']):
    -0.63
    sizeCache
    -0.63
    POSITIVE LOGITS
     for
    0.75
     from
    0.66
     on
    0.66
     that
    0.63
     
    0.60
     and
    0.60
     of
    0.59
     about
    0.59
     with
    0.59
     This
    0.54
    Activations Density 0.018%

    No Known Activations