© 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. 4-CLT-HP
    7. 27
    Prev
    Next
    INDEX
    Explanations

    chest

    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
    abetes
    -0.71
     ladri
    -0.64
    وزی
    -0.62
     prisonniers
    -0.61
    rfloor
    -0.61
     colorés
    -0.60
     générations
    -0.59
     engraçadas
    -0.59
     Kij
    -0.58
     ujednoznacz
    -0.57
    POSITIVE LOGITS
     referenties
    0.47
    ReusableCell
    0.45
     comp
    0.44
     pains
    0.43
     pain
    0.43
    AxisAlignment
    0.43
    yntaxException
    0.42
    pact
    0.41
     initComponents
    0.40
    nodoc
    0.40
    Activations Density 0.002%

    No Known Activations