© 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. 20-CLT-HP
    7. 76464
    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
     scattata
    -0.54
    CloseOperation
    -0.46
     Llor
    -0.45
     Administrativna
    -0.44
    RTLR
    -0.44
    awaiter
    -0.43
    TagMode
    -0.42
    ViewFeatures
    -0.42
     resourceCulture
    -0.41
     ***!
    -0.41
    POSITIVE LOGITS
    esgue
    0.60
    
    0.59
    Demografie
    0.53
     codes
    0.52
    mogorov
    0.52
    Statistiche
    0.50
    ioutil
    0.50
     nonUne
    0.49
    blocks
    0.49
     prosecutions
    0.49
    Activations Density 0.003%

    No Known Activations