© 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. 1391
    Prev
    Next
    INDEX
    Explanations

    tumors

    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
     Theſe
    -0.80
    OGND
    -0.78
     ſeveral
    -0.76
     Engines
    -0.75
     Diſ
    -0.75
     soils
    -0.75
     Soils
    -0.75
     tumours
    -0.75
     knots
    -0.74
     oils
    -0.73
    POSITIVE LOGITS
     of
    0.56
     (
    0.52
     in
    0.50
     CanadaChoose
    0.49
     and
    0.48
     for
    0.48
    .
    0.47
     from
    0.47
    ,
    0.47
     to
    0.46
    Activations Density 0.156%

    No Known Activations