© 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. 30529
    Prev
    Next
    INDEX
    Explanations

    words related to actions or behaviors that are sensory or expressive

    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
    COUVER
    -0.61
    !*\
    -0.60
    mybatisplus
    -0.59
    MENAFN
    -0.57
     שוליים
    -0.57
    酯
    -0.56
    bufio
    -0.55
     famiglia
    -0.53
    TestBed
    -0.52
     ModelExpression
    -0.52
    POSITIVE LOGITS
     Wink
    0.82
     Linger
    0.76
    ftance
    0.75
    ientí
    0.73
    Referències
    0.71
    Lint
    0.70
    ftances
    0.70
     proverbs
    0.69
     Shine
    0.68
     rana
    0.68
    Activations Density 0.061%

    No Known Activations