© 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. 5-CLT-HP
    7. 93509
    Prev
    Next
    INDEX
    Explanations

    actions, touch

    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
    Pro
    -0.46
     skin
    -0.45
    Tip
    -0.44
     McFarland
    -0.43
     tip
    -0.41
     Nail
    -0.41
    lainen
    -0.41
    serv
    -0.40
    PR
    -0.40
    servic
    -0.40
    POSITIVE LOGITS
     tartalomajánló
    0.68
     disambiguazione
    0.67
     <<<<<<<<<<<<<<
    0.66
     препратки
    0.65
     initComponents
    0.64
    StoryboardSegue
    0.64
     Wikimedijinoj
    0.63
    OGND
    0.63
    بوابة
    0.61
    kuuta
    0.60
    Activations Density 0.002%

    No Known Activations