© 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. 1-CLT-HP
    7. 14105
    Prev
    Next
    INDEX
    Explanations

    undergo

    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
    __':
    -0.84
    TagMode
    -0.81
     لينك
    -0.73
    __":
    -0.69
     lccn
    -0.67
    windowFixed
    -0.67
     BoxDecoration
    -0.65
    jsonwebtoken
    -0.63
    rawtypes
    -0.62
     BoxFit
    -0.60
    POSITIVE LOGITS
     a
    0.71
     the
    0.56
     another
    0.53
     sortes
    0.52
    nya
    0.52
     what
    0.52
     an
    0.51
     something
    0.50
     its
    0.49
    orts
    0.48
    Activations Density 0.009%

    No Known Activations