© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43336
    Prev
    Next
    INDEX
    Explanations

    hundreds

    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
     hundreds
    -1.88
    hundreds
    -1.69
     thousands
    -1.60
     Hundreds
    -1.52
    Hundreds
    -1.48
    thousands
    -1.45
     dozens
    -1.38
     cientos
    -1.34
     centaines
    -1.30
    Thousands
    -1.27
    POSITIVE LOGITS
     of
    1.23
     nakalista
    0.61
     percent
    0.57
     or
    0.56
     (
    0.51
    .
    0.49
    Personendaten
    0.49
     and
    0.48
     Of
    0.48
     العنوان
    0.48
    Activations Density 1.733%

    No Known Activations