© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4155
    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
    TagMode
    -0.67
    ques
    -0.54
     Kenobi
    -0.54
     colspan
    -0.52
    intend
    -0.50
     Borne
    -0.50
    ('@
    -0.48
     Kl
    -0.47
    uerdo
    -0.47
     sanitarias
    -0.47
    POSITIVE LOGITS
     lenker
    0.74
     snippetHide
    0.62
     Accesat
    0.57
    homonymie
    0.57
    ViewStyle
    0.52
     Majefty
    0.52
    SharedDtor
    0.51
     arra
    0.50
     كومونز
    0.50
    ätzt
    0.49
    Activations Density 0.005%

    No Known Activations