© 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. 17321
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their associated 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
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAlignment
    -0.63
    ISTICS
    -0.61
     autorytatywna
    -0.61
     ferons
    -0.60
    Athlete
    -0.60
    CrossRef
    -0.59
    Impressum
    -0.59
    OOTDTY
    -0.58
    zust
    -0.57
    Externé
    -0.57
    POSITIVE LOGITS
    دانشنامهٔ
    0.60
    tagHelperRunner
    0.57
    تقاوى
    0.56
    ніципа
    0.54
     Neop
    0.54
    bootstrapcdn
    0.52
     sherds
    0.52
     Hopf
    0.50
     Sver
    0.50
     Euse
    0.49
    Activations Density 0.000%

    No Known Activations