© 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. 91472
    Prev
    Next
    INDEX
    Explanations

    programming and data

    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
    -0.49
    Conclusie
    -0.45
    findpost
    -0.44
    tonode
    -0.43
    følgelig
    -0.42
     setempat
    -0.42
     Lightfoot
    -0.42
    ($__
    -0.41
    cendental
    -0.41
     kasarigan
    -0.41
    POSITIVE LOGITS
    Попис
    0.68
    Portale
    0.66
    velle
    0.59
    wiss
    0.57
    InstanceState
    0.57
     OFDb
    0.57
    routeProvider
    0.56
     profession
    0.55
    ագրություն
    0.55
    afficheront
    0.54
    Activations Density 0.003%

    No Known Activations