© 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. 93025
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ModelExpression
    -0.84
    StructEnd
    -0.83
     AssemblyCulture
    -0.82
    ThroughAttribute
    -0.79
    enterOuterAlt
    -0.75
     AttributeSet
    -0.70
    تقاوى
    -0.70
    afficheront
    -0.70
    цездатний
    -0.67
    SpringRunner
    -0.65
    POSITIVE LOGITS
    rí
    0.49
     gem
    0.48
    Azur
    0.48
     Cass
    0.47
    UserDto
    0.47
    m
    0.46
    TestTools
    0.46
     vesicle
    0.46
       
    0.45
    gem
    0.45
    Activations Density 0.000%

    No Known Activations