© 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. 1010
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and associated words.

    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
     why
    -0.81
    Why
    -0.75
    why
    -0.74
     Why
    -0.69
     Почему
    -0.69
    Warum
    -0.68
     how
    -0.67
    how
    -0.67
    RenderAtEndOf
    -0.65
     Warum
    -0.65
    POSITIVE LOGITS
     Cheers
    1.34
     Regards
    1.25
    Cheers
    1.23
    cheers
    1.18
     cheers
    1.12
    Regards
    1.11
     hope
    1.10
     Hope
    1.09
     Thanks
    1.07
     Happy
    1.06
    Activations Density 0.599%

    No Known Activations