© 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. 23305
    Prev
    Next
    INDEX
    Explanations

    expressive punctuation and emotional tone in writing

    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
    Negative Logits
    DockStyle
    -0.85
     BoxFit
    -0.71
    withIdentifier
    -0.70
     imageNamed
    -0.68
    UseVisualStyle
    -0.64
    glLoadIdentity
    -0.60
    OGND
    -0.60
    HasForeignKey
    -0.59
    medriver
    -0.59
     дописавши
    -0.58
    POSITIVE LOGITS
     overall
    0.75
     Overall
    0.74
    Overall
    0.73
    overall
    0.65
    dziew
    0.55
     verdict
    0.54
     Insgesamt
    0.53
    Verdict
    0.51
    OVERALL
    0.51
    cdnjs
    0.50
    Activations Density 0.097%

    No Known Activations