© 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. 2366
    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
     Monfieur
    -0.70
     myſelf
    -0.69
    Kariera
    -0.67
    localctx
    -0.60
    zessin
    -0.60
     raiſ
    -0.60
    AccessorTable
    -0.60
    ſelf
    -0.60
    ）』
    -0.59
     Theſe
    -0.59
    POSITIVE LOGITS
     تضيفلها
    0.57
    Билгалдахарш
    0.56
     الحره
    0.50
    APORE
    0.47
    Bioaccumulative
    0.46
    PostExecute
    0.44
     pos
    0.43
    THREADS
    0.42
    DeleteBehavior
    0.42
     calendriers
    0.41
    Activations Density 0.000%

    No Known Activations