© 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. 93213
    Prev
    Next
    INDEX
    Explanations

    time/sequence

    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
     esternos
    -0.77
    PHeader
    -0.70
     Pry
    -0.67
    collier
    -0.65
     Perman
    -0.63
    ombes
    -0.63
    LError
    -0.62
    PANY
    -0.61
     intStringLen
    -0.60
     TypeError
    -0.59
    POSITIVE LOGITS
    <bos>
    1.49
    ↵↵
    0.63
     a
    0.56
    '
    0.52
    a
    0.50
     löyty
    0.49
    ’
    0.46
     the
    0.45
     was
    0.44
     were
    0.44
    Activations Density 0.173%

    No Known Activations