© 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. 1-CLT-HP
    4. 11944
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    fekt
    -0.69
    StoryboardSegue
    -0.61
    Hentet
    -0.60
     fhew
    -0.60
     disambiguazione
    -0.60
     ſtand
    -0.59
     dreht
    -0.58
     Архів
    -0.57
    '}>
    -0.57
    SequentialGroup
    -0.56
    POSITIVE LOGITS
    mybatisplus
    0.57
    rungsseite
    0.50
     onPostExecute
    0.46
     exc
    0.46
    WireFormat
    0.45
    DEEP
    0.43
    ChildScrollView
    0.43
    Bien
    0.42
    cated
    0.42
    dot
    0.41
    Activations Density 2.149%

    No Known Activations