© 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. 5-CLT-HP
    7. 97884
    Prev
    Next
    INDEX
    Explanations

    to

    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
     AssemblyProduct
    -0.63
    ⓧ
    -0.59
    bootstrapcdn
    -0.55
     jspb
    -0.55
    oneofs
    -0.53
    upaten
    -0.52
    illary
    -0.49
    GLenum
    -0.49
     Hermans
    -0.48
     Signalez
    -0.47
    POSITIVE LOGITS
    Adding
    0.67
     happening
    0.64
     finding
    0.63
    finding
    0.62
     messing
    0.62
     Adding
    0.60
     adding
    0.60
    PyExc
    0.56
     ending
    0.55
    adding
    0.55
    Activations Density 0.002%

    No Known Activations