© 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. 14257
    Prev
    Next
    INDEX
    Explanations

    numerical representations or codes often associated with classification or categorization systems

    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
    +#+#
    -0.63
    లాలు
    -0.62
    itinéraire
    -0.60
    +#+
    -0.59
    InSection
    -0.59
     IndexPath
    -0.59
    RRect
    -0.57
    UIControlState
    -0.55
     OFDb
    -0.53
    ########.
    -0.52
    POSITIVE LOGITS
     Jue
    0.50
     Offisielt
    0.49
    UserScript
    0.45
    kingen
    0.44
     shah
    0.44
    تقاوى
    0.44
    Билгалдахарш
    0.44
     Boga
    0.44
     vetores
    0.44
    ValueStyle
    0.43
    Activations Density 0.003%

    No Known Activations