© 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. 91426
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
    WebServlet
    -0.96
     beginnetje
    -0.92
    rungsseite
    -0.86
    Personensuche
    -0.86
     resourceCulture
    -0.85
    SourceChecksum
    -0.84
    GEBURTSDATUM
    -0.84
    expandindo
    -0.83
    AnimationsModule
    -0.82
    Sucesor
    -0.80
    POSITIVE LOGITS
    scs
    0.49
     façons
    0.49
    *>(
    0.46
    reid
    0.45
     तरह
    0.45
     Sind
    0.42
    isEqual
    0.42
     skjer
    0.42
     parecer
    0.41
    type
    0.40
    Activations Density 0.013%

    No Known Activations