© 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. 76641
    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
     like
    -0.84
     soos
    -0.70
    Like
    -0.61
     referenties
    -0.56
    like
    -0.56
     nagu
    -0.56
    Hozzáférés
    -0.56
    HomeAsUpEnabled
    -0.55
    IntoConstraints
    -0.55
    kannya
    -0.55
    POSITIVE LOGITS
     this
    0.89
     cherchés
    0.55
    findpost
    0.54
    InjectAttribute
    0.51
     dieser
    0.51
     този
    0.50
     tills
    0.50
     AssemblyTitle
    0.49
    TagMode
    0.48
    this
    0.47
    Activations Density 0.000%

    No Known Activations