© 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. 97116
    Prev
    Next
    INDEX
    Explanations

    Measurements

    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
     the
    -1.00
     g
    -0.91
     an
    -0.87
     d
    -0.87
     m
    -0.87
     t
    -0.85
     l
    -0.85
     all
    -0.84
     a
    -0.82
     h
    -0.82
    POSITIVE LOGITS
     myſelf
    1.65
     itſelf
    1.61
     ſche
    1.47
     ―――――
    1.47
     houſe
    1.45
     faſt
    1.45
     Majefty
    1.44
     Houſe
    1.43
     Jefus
    1.42
     Efq
    1.42
    Activations Density 0.174%

    No Known Activations