© 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. 38648
    Prev
    Next
    INDEX
    Explanations

    Government/Meeting

    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
    RenderAtEndOf
    -1.13
     itſelf
    -1.02
     Jefus
    -0.88
     myſelf
    -0.86
     Majefty
    -0.85
    EndContext
    -0.84
     poffible
    -0.84
     himſelf
    -0.82
     raiſ
    -0.81
    ſelves
    -0.80
    POSITIVE LOGITS
     the
    0.70
     an
    0.59
     their
    0.57
     a
    0.55
     any
    0.53
     your
    0.52
     what
    0.52
     me
    0.49
     some
    0.48
     all
    0.48
    Activations Density 0.009%

    No Known Activations