© 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. 41172
    Prev
    Next
    INDEX
    Explanations

    environments

    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
     Monfieur
    -1.21
     myſelf
    -1.15
     itſelf
    -1.10
     Theſe
    -1.05
     pleaſure
    -1.05
     faſt
    -1.02
     Diſ
    -1.00
     Reſ
    -1.00
     Jefus
    -0.98
     Efq
    -0.98
    POSITIVE LOGITS
     ber
    0.57
     handle
    0.56
     m
    0.55
     to
    0.55
     model
    0.55
     for
    0.54
     rest
    0.53
     (
    0.52
     no
    0.52
     "
    0.51
    Activations Density 1.231%

    No Known Activations