© 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. 9272
    Prev
    Next
    INDEX
    Explanations

    terminology related to uniqueness or differentiation

    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
    '}>
    -1.02
     ***/
    -0.96
     Horv
    -0.92
    ंदीखरीदारी
    -0.88
    ]-->
    -0.88
    monary
    -0.86
    <()>
    -0.85
     tartalomajánló
    -0.85
    rehensive
    -0.84
    --]
    -0.84
    POSITIVE LOGITS
    INCT
    0.81
    ness
    0.77
     tortas
    0.61
    next
    0.58
    odacty
    0.58
    :✨
    0.57
    inct
    0.56
     Eis
    0.56
     Jay
    0.56
     Jays
    0.56
    Activations Density 0.005%

    No Known Activations