© 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. 20-CLT-HP
    7. 76031
    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
     Wikimedijinoj
    -0.66
    醐
    -0.63
    affaires
    -0.60
     AssemblyCulture
    -0.59
    principalTable
    -0.57
     Godhead
    -0.57
    autorest
    -0.57
    redited
    -0.57
    parsedMessage
    -0.54
     authorized
    -0.54
    POSITIVE LOGITS
     صوتيه
    0.51
     AssemblyProduct
    0.50
    Enllaces
    0.45
     ostavi
    0.44
    Спољашње
    0.40
    Raphael
    0.39
    __':
    0.39
     GIR
    0.39
     AssemblyTitle
    0.39
    OrNil
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.