© 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. 20-CLT-HP
    7. 75286
    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
     neither
    -0.65
    neither
    -0.64
    bootstrapcdn
    -0.63
     nenhuma
    -0.55
    Neither
    -0.55
     Neither
    -0.54
    enterOuterAlt
    -0.52
     none
    -0.52
     żad
    -0.52
     jauh
    -0.50
    POSITIVE LOGITS
     likely
    0.68
     I
    0.65
    جغرافيا
    0.61
    likely
    0.53
    ulkner
    0.52
     resourceCulture
    0.52
     بيها
    0.52
    acon
    0.52
     to
    0.52
    encodeWith
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.