© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 247
    Prev
    Next
    INDEX
    Explanations

    references to people speaking, particularly names followed by verbs like "said".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    ίναι
    -0.55
    interopRequire
    -0.53
    TagMode
    -0.49
     Cientí
    -0.49
    Rohy
    -0.49
    Taken
    -0.49
    ỡng
    -0.49
    Numerology
    -0.48
    Datuak
    -0.48
     -¿
    -0.48
    POSITIVE LOGITS
     said
    2.19
     says
    1.87
     stated
    1.69
    said
    1.69
     say
    1.68
     saying
    1.63
    Said
    1.48
     SAID
    1.41
     mengatakan
    1.41
    says
    1.40
    Activations Density 2.571%

    No Known Activations