© 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. 0-CLT-HP
    7. 42825
    Prev
    Next
    INDEX
    Explanations

    only

    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
    StoryboardSegue
    -0.63
    GEBURTS
    -0.60
     فريبيس
    -0.58
     propOrder
    -0.58
    Personensuche
    -0.55
    saraba
    -0.54
    evich
    -0.54
    writeFieldEnd
    -0.54
    OGND
    -0.52
     ujednoznacz
    -0.52
    POSITIVE LOGITS
     transcriptional
    0.62
     apoptosis
    0.60
     transfection
    0.59
     fusca
    0.59
     glandular
    0.59
     polyn
    0.58
     buoyancy
    0.57
     transcription
    0.55
     disinfection
    0.55
     polymorphisms
    0.55
    Activations Density 0.165%

    No Known Activations