© 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. 12192
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with specific attributes or categories in data structures

    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
    ...)
    -0.52
    ciclop
    -0.51
     كمان
    -0.45
     ...)
    -0.44
     etc
    -0.43
     /^\
    -0.43
    ...")
    -0.42
    %}
    -0.42
    ց
    -0.41
    salvar
    -0.40
    POSITIVE LOGITS
    hoeddwyd
    0.70
    Geplaatst
    0.62
    الدراسه
    0.61
    Personendaten
    0.61
    featureID
    0.60
    basicConfig
    0.59
    twimg
    0.58
     незавершена
    0.57
     Schwert
    0.57
     Missy
    0.56
    Activations Density 0.078%

    No Known Activations