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. 15539
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

    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
    Personendaten
    -0.90
    ValueStyle
    -0.89
     Meksiku
    -0.82
    :✨
    -0.80
    GEBURTSDATUM
    -0.79
    CreateMap
    -0.75
    MigrationBuilder
    -0.74
    __*/
    -0.72
    InputBorder
    -0.71
    StreetMap
    -0.66
    POSITIVE LOGITS
    AppMethodBeat
    0.52
    elis
    0.47
     intptr
    0.45
    قرأ
    0.44
    jeva
    0.44
    INCREF
    0.43
    delen
    0.43
    cheng
    0.42
    فيذ
    0.42
    からだ
    0.42
    Activations Density 0.002%

    No Known Activations