© 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. 24964
    Prev
    Next
    INDEX
    Explanations

    elements related to color, specifically in visual or design contexts

    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
     getItemId
    -0.51
    greja
    -0.48
    istle
    -0.47
     koniecz
    -0.47
    NUMX
    -0.46
     Slade
    -0.46
    olsom
    -0.46
    écnicas
    -0.44
    ulipas
    -0.44
    */;
    -0.44
    POSITIVE LOGITS
     متعلقه
    0.70
    mybatisplus
    0.69
     beginnetje
    0.60
     setuptools
    0.56
    ⓧ
    0.56
    احب
    0.56
    ########.
    0.56
    הערות
    0.55
    DockStyle
    0.55
    tvguidetime
    0.55
    Activations Density 0.356%

    No Known Activations