© 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. 19282
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to energy and chemical reactions

    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
     mest
    -0.44
     davon
    -0.42
    mest
    -0.42
     growing
    -0.40
    Glej
    -0.40
     J
    -0.39
    -
    -0.39
     grow
    -0.38
    Growing
    -0.38
     var
    -0.37
    POSITIVE LOGITS
    setVerticalGroup
    0.92
    ValueStyle
    0.92
    RenderAtEndOf
    0.85
    InSection
    0.85
    sizeCache
    0.84
    UnusedPrivate
    0.84
    MigrationBuilder
    0.82
    ########.
    0.79
    IsUnicode
    0.78
    addCriterion
    0.76
    Activations Density 0.063%

    No Known Activations