© 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. 71904
    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
     étroite
    -0.70
     noires
    -0.66
     acrylique
    -0.64
     démocr
    -0.61
     sagesse
    -0.59
     étro
    -0.58
    ceptre
    -0.57
     nationales
    -0.57
     fédé
    -0.57
     strå
    -0.57
    POSITIVE LOGITS
    OGND
    0.65
     الرياضيه
    0.53
    ()]);
    0.52
    yntaxException
    0.52
     ErrIntOverflow
    0.52
    LookAnd
    0.52
    StructEnd
    0.52
     nonUne
    0.51
    Aholisi
    0.49
    Datuak
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.