© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92284
    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
    شنامه
    -0.42
    Extinguishing
    -0.41
    live
    -0.40
     Landes
    -0.39
    foot
    -0.39
     setEmail
    -0.39
     kapp
    -0.39
     Zjednoc
    -0.39
     digress
    -0.38
     nerv
    -0.36
    POSITIVE LOGITS
    AndEndTag
    0.90
    djangoproject
    0.73
    Tikang
    0.73
    Jeografia
    0.71
     незавершена
    0.68
    XmlEnum
    0.67
    TagMode
    0.67
     betweenstory
    0.66
     kasarigan
    0.65
     وتسجيلات
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.