© 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. 11823
    Prev
    Next
    INDEX
    Explanations

    in

    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
     
    -0.60
     in
    -0.55
     beginnetje
    -0.53
     (
    -0.50
     No
    -0.48
     at
    -0.48
     as
    -0.46
     S
    -0.46
     In
    -0.45
     general
    -0.45
    POSITIVE LOGITS
    rrggbb
    1.00
     myſelf
    0.97
     purpoſe
    0.95
     Houſe
    0.94
     Monfieur
    0.94
    abetes
    0.89
     שוליים
    0.88
     photolibrary
    0.85
     houſe
    0.84
     Efq
    0.84
    Activations Density 0.014%

    No Known Activations