© 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. 5-CLT-HP
    7. 92012
    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
    ViewFeatures
    -0.73
    Personendaten
    -0.68
     "..\..\..\
    -0.67
    ImageContext
    -0.67
    windowFixed
    -0.66
     estekak
    -0.63
     kasarigan
    -0.60
    FieldBuilder
    -0.59
    OGND
    -0.59
    Tembelea
    -0.57
    POSITIVE LOGITS
     actionMode
    0.48
     Presidencia
    0.47
    inkov
    0.47
     odeur
    0.47
    DECLARE
    0.46
    zunehmen
    0.46
     Cute
    0.46
    TextInputLayout
    0.45
     Stampa
    0.45
     Lacy
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.