© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13354
    Prev
    Next
    INDEX
    Explanations

    one

    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
    WillAppear
    -0.61
    tonsoft
    -0.56
    Portály
    -0.54
    Và
    -0.53
     Egyes
    -0.52
    RuleContext
    -0.52
     chileno
    -0.50
    canestro
    -0.49
     Chilean
    -0.49
    ㅐ
    -0.49
    POSITIVE LOGITS
     समीक्षाओं
    0.64
    parsedMessage
    0.63
    évaluateur
    0.58
     Bhu
    0.53
     समीक्षक
    0.52
    StoryboardSegue
    0.52
     Arjuna
    0.52
    JsonFormat
    0.52
     crore
    0.52
     Constitu
    0.52
    Activations Density 0.024%

    No Known Activations