© 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. 17314
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or speech in a document

    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
    engah
    -0.51
    '},
    -0.49
    WriteBarrier
    -0.47
    adaptiveStyles
    -0.45
    ãng
    -0.45
    Zir
    -0.44
    Extend
    -0.43
     closely
    -0.42
     Bereits
    -0.42
    '))
    -0.42
    POSITIVE LOGITS
     كومونز
    0.72
    inghouse
    0.68
     kysy
    0.68
    AddTagHelper
    0.66
    ineno
    0.66
    zielle
    0.66
     esterni
    0.65
    writeField
    0.65
     Tooth
    0.62
     للاسماء
    0.60
    Activations Density 0.032%

    No Known Activations