© 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. 22-RES-MATRYOSHKA-DC
    7. 2517
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in specific patterns

    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
    Datuak
    -0.54
     sadly
    -0.51
     unfortunately
    -0.50
     note
    -0.48
     proszę
    -0.48
    jande
    -0.48
     I
    -0.47
     niestety
    -0.46
     recomendo
    -0.46
     please
    -0.46
    POSITIVE LOGITS
     Whether
    1.11
    Whether
    1.06
     whether
    1.03
    whether
    0.97
     WHETHER
    0.93
    ftagPool
    0.84
     Discover
    0.80
     Want
    0.78
    Discover
    0.76
    Want
    0.76
    Activations Density 0.218%

    No Known Activations