© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41494
    Prev
    Next
    INDEX
    Explanations

    such

    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
    -2.23
     pleaſure
    -2.20
     itſelf
    -2.13
     Majefty
    -2.06
     Efq
    -2.05
     Monfieur
    -2.05
     photolibrary
    -1.93
     purpoſe
    -1.91
     Jefus
    -1.87
     Shakspeare
    -1.84
    POSITIVE LOGITS
     
    1.18
    <eos>
    1.12
     S
    1.08
     of
    0.99
     B
    0.99
     C
    0.98
     R
    0.97
     a
    0.96
     c
    0.94
     (
    0.93
    Activations Density 0.161%

    No Known Activations