© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98096
    Prev
    Next
    INDEX
    Explanations

    sickness

    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
    AndEndTag
    -0.80
    rungsseite
    -0.77
    __(/*!
    -0.69
    WindowConstants
    -0.68
     дописавши
    -0.68
    UIControlState
    -0.66
    +:+
    -0.64
    SequentialGroup
    -0.64
     
    -0.62
    '])){
    -0.62
    POSITIVE LOGITS
     to
    0.61
    a
    0.53
    ous
    0.45
    sto
    0.45
     stomach
    0.43
    bag
    0.42
     tum
    0.41
    bud
    0.41
     Stomach
    0.40
    as
    0.40
    Activations Density 0.003%

    No Known Activations