© 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. 1178
    Prev
    Next
    INDEX
    Explanations

    epidemiological

    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
    oose
    -0.55
     estekak
    -0.55
     Intr
    -0.54
     continuant
    -0.53
     Urs
    -0.52
    oneph
    -0.52
     disponibilités
    -0.51
     glucocortico
    -0.51
    Παραπομπές
    -0.51
     Pren
    -0.51
    POSITIVE LOGITS
    mio
    0.82
    mics
    0.60
    mic
    0.57
    mil
    0.56
    FieldBuilder
    0.50
    modelBuilder
    0.50
    modb
    0.48
     mxArray
    0.45
    Vidite
    0.44
    enumii
    0.44
    Activations Density 0.020%

    No Known Activations