© 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. 76718
    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
    nada
    -0.50
     Wikimedijinoj
    -0.50
    lös
    -0.48
     Lungen
    -0.47
    まさ
    -0.47
    ücken
    -0.47
    rac
    -0.46
    ösungen
    -0.46
    èdia
    -0.46
    جمعیت
    -0.45
    POSITIVE LOGITS
     rootReducer
    0.62
    jupiter
    0.56
     newBuilder
    0.56
    "):
    0.56
    )]:
    0.52
    ⓧ
    0.52
    "];
    0.52
    SequentialGroup
    0.51
    ":["
    0.50
    featureID
    0.50
    Activations Density 0.002%

    No Known Activations