© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10901
    Prev
    Next
    INDEX
    Explanations

    file paths and references, particularly in a coding or programming context

    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
     ostavi
    -1.06
     betweenstory
    -1.04
    MigrationBuilder
    -1.03
    LookAnd
    -1.02
    GraphicsUnit
    -0.97
    AddTagHelper
    -0.93
     EconPapers
    -0.93
    ValueStyle
    -0.85
    TintMode
    -0.82
    WebElementEntity
    -0.82
    POSITIVE LOGITS
    atoms
    0.46
    imageshack
    0.45
     bruk
    0.43
    ノロ
    0.43
    makedirs
    0.42
     لينك
    0.42
     ruines
    0.41
    gaben
    0.41
     atoms
    0.40
     domicilio
    0.40
    Activations Density 0.002%

    No Known Activations