© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 10885
    Prev
    Next
    INDEX
    Explanations

    references to links and URLs

    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
    +#+#
    -0.68
    المكان
    -0.56
    #
    -0.52
    findpost
    -0.51
     GenerationType
    -0.50
    astéroïdes
    -0.50
     resourceCulture
    -0.49
     perpendicular
    -0.48
     nuns
    -0.48
     Bantam
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.61
    GetAxis
    0.53
     jScrollPane
    0.52
    onBackPressed
    0.51
    LANTA
    0.49
     Fibers
    0.49
    Enregistrer
    0.48
    RectangleBorder
    0.47
     Bracket
    0.47
    imantan
    0.47
    Activations Density 0.145%

    No Known Activations