© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 114
    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
    rosen
    -0.48
    ari
    -0.44
    wär
    -0.42
     pol
    -0.42
    InputTagHelper
    -0.41
    setGeometry
    -0.41
     Artículos
    -0.41
     And
    -0.40
     Cress
    -0.40
    itze
    -0.40
    POSITIVE LOGITS
    ########.
    1.00
    principalTable
    0.84
    parsedMessage
    0.73
    PerformLayout
    0.72
    uxxxx
    0.71
     الحره
    0.70
     pageContext
    0.69
    ագրություններ
    0.69
    tvguidetime
    0.66
    rrggbb
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.