© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14546
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to shaking or similar physical movements

    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
    ंदीखरीदारी
    -0.61
    LLocation
    -0.60
    thington
    -0.59
    mpc
    -0.59
    essentiel
    -0.59
    ḵ
    -0.57
    land
    -0.56
    Ⓢ
    -0.55
    sv
    -0.55
     Gand
    -0.55
    POSITIVE LOGITS
     Shake
    1.52
     shake
    1.52
     shakes
    1.48
    shake
    1.46
    Shake
    1.45
     shaken
    1.41
     shaking
    1.38
     shook
    1.36
     Shakes
    1.26
    shakes
    1.26
    Activations Density 0.009%

    No Known Activations