Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 18657
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and formatting symbols used in coding or markup languages

    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
    Vidite
    -1.18
    Personensuche
    -1.11
     protoimpl
    -1.09
    featureID
    -1.08
    UnusedPrivate
    -1.03
    MessageOf
    -1.02
    MigrationBuilder
    -1.01
     Италијани
    -1.00
    IndentedString
    -1.00
    FunctionFlags
    -0.97
    POSITIVE LOGITS
     hung
    0.37
    quial
    0.36
    :
    0.36
    きた
    0.35
     scu
    0.34
    res
    0.34
    споль
    0.34
    عة
    0.33
    zieć
    0.33
    捺
    0.33
    Activations Density 0.180%

    No Known Activations