© 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. 0-CLT-HP
    7. 1363
    Prev
    Next
    INDEX
    Explanations

    chemical, scientific research

    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
     myſelf
    -1.32
     itſelf
    -1.30
     Efq
    -1.27
     Monfieur
    -1.27
     Jefus
    -1.25
    parsedMessage
    -1.21
     Shakspeare
    -1.20
     pleaſure
    -1.17
    ſelf
    -1.12
    StoryboardSegue
    -1.11
    POSITIVE LOGITS
     
    0.74
    1
    0.73
    2
    0.73
    s
    0.70
     (
    0.67
     “
    0.67
    7
    0.66
    0
    0.65
    4
    0.65
    n
    0.65
    Activations Density 0.398%

    No Known Activations