© 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. 1-CLT-HP
    4. 671
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    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
    Zeneca
    -0.63
    +#+#
    -0.60
    SOUNDBITE
    -0.56
     BoxFit
    -0.56
     Namely
    -0.54
    Probably
    -0.53
    ſelf
    -0.52
     laſt
    -0.52
     faſt
    -0.52
     inconnu
    -0.50
    POSITIVE LOGITS
     I
    0.79
     he
    0.70
     it
    0.65
     an
    0.59
     we
    0.59
     you
    0.57
     the
    0.56
    bootstrapcdn
    0.53
     they
    0.53
     a
    0.52
    Activations Density 0.017%

    No Known Activations