© 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. 8986
    Prev
    Next
    INDEX
    Explanations

    punctuations and separator characters

    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
    "]];
    -0.71
     }}$}
    -0.70
    Vidite
    -0.70
    "];
    -0.65
    "])
    -0.65
     Offisielt
    -0.65
    "]));
    -0.65
    '])
    -0.64
    '])->
    -0.64
    Anhalt
    -0.64
    POSITIVE LOGITS
    bootstrapcdn
    0.80
    CDCl
    0.64
    IsContent
    0.63
    出版年
    0.58
    jsdelivr
    0.57
    atrici
    0.55
     themes
    0.55
     Magn
    0.52
    ودة
    0.52
    RelativeTo
    0.52
    Activations Density 0.343%

    No Known Activations