© 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. 24699
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to session management in programming contexts

    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
    isTrue
    -0.67
    stri
    -0.65
    ाई
    -0.63
     kı
    -0.61
    Cruel
    -0.59
    __);
    -0.59
    WriteLine
    -0.57
    Kön
    -0.57
     Scand
    -0.57
     Brü
    -0.57
    POSITIVE LOGITS
     session
    1.65
     Session
    1.65
     Sessions
    1.61
    sessions
    1.60
     sessions
    1.59
     SESSION
    1.55
    session
    1.48
    SESSION
    1.48
    Session
    1.47
    Sessions
    1.45
    Activations Density 0.011%

    No Known Activations