© 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. 97710
    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
    ⓘ
    -0.66
     الحره
    -0.49
     متعلقه
    -0.48
    <eos>
    -0.46
     lej
    -0.46
    liothèque
    -0.45
    ề
    -0.45
    〉
    -0.45
    ioutil
    -0.44
    __':
    -0.43
    POSITIVE LOGITS
     pleaſure
    0.70
     preſent
    0.69
     ſeveral
    0.68
     fometimes
    0.67
     reaſon
    0.66
     betweenstory
    0.66
     ſmall
    0.64
     juſt
    0.64
     itſelf
    0.64
     ſtate
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.