© 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. 8958
    Prev
    Next
    INDEX
    Explanations

    references to conditional or descriptive phrases that establish relationships or characteristics

    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
     mati
    -0.38
     point
    -0.38
     re
    -0.38
     carta
    -0.38
     air
    -0.37
    ји
    -0.37
     mor
    -0.37
    ラ
    -0.37
     “
    -0.36
     wij
    -0.36
    POSITIVE LOGITS
    contentLoaded
    1.30
     unknownFields
    1.10
    LookAnd
    1.05
    Rüyada
    1.00
    WarningLevel
    1.00
    ьаж
    0.98
    UnknownFieldSet
    0.97
    UrlEncoded
    0.94
    хьтан
    0.92
    
    0.91
    Activations Density 0.114%

    No Known Activations