© 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. 92285
    Prev
    Next
    INDEX
    Explanations

    tangible

    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
     Majefty
    -1.05
    ſelf
    -1.02
     myſelf
    -1.00
    ̈́
    -0.97
     houſe
    -0.95
     purpoſe
    -0.94
     Theſe
    -0.92
     itſelf
    -0.90
     ſtate
    -0.90
     ſta
    -0.88
    POSITIVE LOGITS
     or
    0.53
     of
    0.41
    ↵↵
    0.41
     sign
    0.40
     UIImage
    0.40
     and
    0.40
    bas
    0.40
    ,
    0.40
     combination
    0.39
     `
    0.39
    Activations Density 0.049%

    No Known Activations