© 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. 3289
    Prev
    Next
    INDEX
    Explanations

    punctuation and numerical patterns in the text

    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
    both
    -0.52
     both
    -0.49
     оригіналу
    -0.48
    Naissance
    -0.47
    joje
    -0.47
    gwt
    -0.46
     Inscrivez
    -0.46
    どちらも
    -0.45
     najwyżs
    -0.45
     confronti
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.75
    dymyr
    0.70
    DoubleQuotes
    0.69
     الحره
    0.69
    StoryboardSegue
    0.68
    onoi
    0.68
    UPAC
    0.65
     createSlice
    0.65
    曖昧さ回避
    0.64
    migrationBuilder
    0.63
    Activations Density 0.028%

    No Known Activations