© 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. 6139
    Prev
    Next
    INDEX
    Explanations

    references to signals and their qualities

    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
     Bux
    -0.74
    Климат
    -0.67
    asthan
    -0.64
    Maur
    -0.63
    DeleteBehavior
    -0.63
     Yeats
    -0.63
     memp
    -0.62
    ykite
    -0.62
     Baxter
    -0.60
    copo
    -0.60
    POSITIVE LOGITS
     Signals
    1.62
     signals
    1.57
    signals
    1.55
     Signal
    1.45
    SIGNAL
    1.38
     signal
    1.36
     SIGNAL
    1.36
    signal
    1.35
    Signals
    1.34
    Signal
    1.27
    Activations Density 0.039%

    No Known Activations