© 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. 5-CLT-HP
    4. 96575
    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
    tieth
    -0.60
    Rüyada
    -0.60
     Infórmanos
    -0.55
    XtraReports
    -0.54
     vôtre
    -0.49
    Elijah
    -0.48
     المعرف
    -0.47
    thâu
    -0.45
    mogelijk
    -0.45
    Dalton
    -0.45
    POSITIVE LOGITS
     BorderRadius
    0.65
     مواليد
    0.60
    yntaxException
    0.59
    SupportActionBar
    0.58
    FetchType
    0.57
    GIVEREF
    0.56
     morire
    0.56
    abetes
    0.56
     Hera
    0.54
    ||}
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.