© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71305
    Prev
    Next
    INDEX
    Explanations

    "ester" sound/name

    np_max-act-logits · 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
    Negative Logits
    }{*}{
    -0.58
    httphttps
    -0.56
    Diwedd
    -0.56
    >";
    -0.54
    :]:
    -0.52
    Gemeinden
    -0.52
    +#+#
    -0.51
    sptr
    -0.51
    EDEFAULT
    -0.50
    HtmlAttribute
    -0.50
    POSITIVE LOGITS
    num
    0.58
    nities
    0.52
    nium
    0.52
     kasarigan
    0.51
    ility
    0.50
    DockStyle
    0.49
    nellement
    0.49
    ns
    0.47
    ei
    0.47
    nal
    0.47
    Activations Density 0.005%

    No Known Activations