© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92383
    Prev
    Next
    INDEX
    Explanations

    hints, brands, "Unt"

    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
     Ambassadors
    -0.98
     itſelf
    -0.98
     myſelf
    -0.93
     Cæsar
    -0.91
     ་་
    -0.88
     Jefus
    -0.88
     Efq
    -0.86
     ambassadors
    -0.85
     Shakspeare
    -0.85
     ſever
    -0.85
    POSITIVE LOGITS
    cadi
    0.60
    cah
    0.52
     place
    0.49
    уна
    0.48
    []
    0.47
     peran
    0.47
     on
    0.45
     mã
    0.45
     than
    0.44
    āci
    0.43
    Activations Density 0.083%

    No Known Activations