© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 75150
    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
     lenker
    -0.61
     reverber
    -0.50
    gents
    -0.50
    antoms
    -0.48
    niko
    -0.45
    Déc
    -0.44
     Michi
    -0.43
     parochial
    -0.43
     echoed
    -0.42
     sapin
    -0.42
    POSITIVE LOGITS
    enumi
    0.82
    InstanceState
    0.67
    +#+#
    0.65
    Personendaten
    0.65
     للمعارف
    0.62
    __*/
    0.61
    posedge
    0.60
    djangoproject
    0.60
    XMLSchema
    0.59
    enumii
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.