© 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. 12335
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    Tracce
    -0.56
     "
    -0.46
     “
    -0.43
     miljø
    -0.42
    =@"
    -0.41
    ã
    -0.39
     PartialEq
    -0.39
     .
    -0.39
    Portale
    -0.38
    پول
    -0.38
    POSITIVE LOGITS
    zbęd
    0.91
    Hochspringen
    0.88
    tvguidetime
    0.81
     صوتيه
    0.79
    Skocz
    0.76
    enumi
    0.75
    "],
    0.74
     BoxFit
    0.72
     courseId
    0.71
    ंदीखरीदारी
    0.71
    Activations Density 0.014%

    No Known Activations