© 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. 8570
    Prev
    Next
    INDEX
    Explanations

    specific numerical patterns or sequences within data

    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
     Tr
    -0.53
     Administrativna
    -0.53
     Saints
    -0.53
     longer
    -0.51
    стей
    -0.51
     Tre
    -0.51
     CONT
    -0.51
    leg
    -0.50
    Eloquent
    -0.50
    oben
    -0.50
    POSITIVE LOGITS
    ValueStyle
    0.74
     AssemblyTitle
    0.68
    AssignableFrom
    0.66
    DOCTYPE
    0.65
    \{\\
    0.62
    PyExc
    0.62
     rêver
    0.62
     extérieurs
    0.60
    нодоро
    0.58
     digitais
    0.57
    Activations Density 0.001%

    No Known Activations