© 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. 45423
    Prev
    Next
    INDEX
    Explanations

    repudi

    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
    AndEndTag
    -1.29
     myſelf
    -1.18
    principalColumn
    -1.16
     purpoſe
    -1.14
     itſelf
    -1.13
     Jefus
    -1.09
     Monfieur
    -1.08
    UnusedPrivate
    -1.07
    ſelf
    -1.06
     Theſe
    -1.06
    POSITIVE LOGITS
     
    0.68
     B
    0.65
     (
    0.65
    ↵↵
    0.64
     b
    0.61
     J
    0.61
     K
    0.60
     k
    0.59
     T
    0.58
     P
    0.57
    Activations Density 0.137%

    No Known Activations