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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1669
    Prev
    Next
    INDEX
    Explanations

    conjunctions that indicate reasons or causes

    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
    joys
    -0.77
    Izvori
    -0.76
    styleUrls
    -0.73
    winston
    -0.71
    MigrationBuilder
    -0.69
    AFTA
    -0.68
     Lockheed
    -0.68
    SuppressLint
    -0.68
    SaveChanges
    -0.67
    fjspx
    -0.67
    POSITIVE LOGITS
     Cuz
    0.98
    ECAUSE
    0.87
     Porque
    0.86
    Because
    0.83
     BECAUSE
    0.83
    Cuz
    0.82
     Parce
    0.81
     Because
    0.78
     Perché
    0.75
    because
    0.74
    Activations Density 0.141%

    No Known Activations