© 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. 29901
    Prev
    Next
    INDEX
    Explanations

    expressions of audience reactions and emotions

    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
    RTEX
    -0.60
    AccessorTable
    -0.59
    rungsseite
    -0.58
    saraba
    -0.58
    featureID
    -0.57
    tvguidetime
    -0.57
    verifyException
    -0.57
    PMailer
    -0.56
    HtmlAttribute
    -0.55
    principalColumn
    -0.54
    POSITIVE LOGITS
    crowd
    0.81
     crowd
    0.78
     Crowd
    0.78
    Crowd
    0.74
     cheering
    0.73
     penonton
    0.68
     crowds
    0.67
     spectators
    0.65
    fans
    0.63
     Zuschauer
    0.63
    Activations Density 0.056%

    No Known Activations