© 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. 4-CLT-HP
    7. 1812
    Prev
    Next
    INDEX
    Explanations

    rheumat

    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
    Personensuche
    -0.63
    homonymie
    -0.61
    UnusedPrivate
    -0.60
    sizeCache
    -0.57
     ModelExpression
    -0.56
     defaultstate
    -0.56
     nakalista
    -0.55
    ellees
    -0.54
     Empieza
    -0.53
     AssemblyProduct
    -0.53
    POSITIVE LOGITS
    oid
    0.85
    iod
    0.71
    hoid
    0.60
    oids
    0.59
    loid
    0.55
     oid
    0.55
    oidal
    0.54
    oida
    0.53
    id
    0.50
     id
    0.48
    Activations Density 0.003%

    No Known Activations