© 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. 12-RES-MATRYOSHKA-DC
    7. 3360
    Prev
    Next
    INDEX
    Explanations

    descriptions of smoothness and fluidity in processes or experiences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sentry
    -0.70
     متعلقه
    -0.69
    __':
    -0.68
    googleapis
    -0.67
     Dage
    -0.67
     Burs
    -0.63
    Kelvin
    -0.63
    ganu
    -0.62
    Personensuche
    -0.62
     GenerationType
    -0.61
    POSITIVE LOGITS
     Smooth
    1.57
    Smooth
    1.52
    smooth
    1.52
     smooth
    1.40
     SMO
    1.30
     smoothness
    1.29
     lisse
    1.27
     smoothed
    1.26
     smoothly
    1.22
     smoother
    1.13
    Activations Density 0.026%

    No Known Activations