© 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. 23362
    Prev
    Next
    INDEX
    Explanations

    statements of fact or certainty

    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
     dover
    -0.53
    andan
    -0.50
     Morgen
    -0.50
     conclusion
    -0.49
     dis
    -0.49
    iyle
    -0.48
     setDate
    -0.48
    Conclusion
    -0.48
     đương
    -0.47
    哉
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.96
    +#+#
    0.96
    IntoConstraints
    0.91
     useRef
    0.90
    nonatomic
    0.85
    parsedMessage
    0.84
    bkz
    0.83
    RuleContext
    0.81
     nonatomic
    0.78
     <=",
    0.77
    Activations Density 0.007%

    No Known Activations