© 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. 32600
    Prev
    Next
    INDEX
    Explanations

    questions related to programming or software development

    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
     
    -0.45
    ...
    -0.45
    '
    -0.44
    -
    -0.39
    Yes
    -0.38
     Res
    -0.38
    www
    -0.36
    (
    -0.36
    A
    -0.36
     b
    -0.36
    POSITIVE LOGITS
     виправивши
    1.47
    InjectAttribute
    1.26
    دانشنامهٔ
    1.18
    parsedMessage
    1.18
    évaluateur
    1.17
     CreateTagHelper
    1.16
    MessageTagHelper
    1.13
     متعلقه
    1.11
    SourceChecksum
    1.09
    Personensuche
    1.08
    Activations Density 0.003%

    No Known Activations