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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5403
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "part" and its derivatives in a technical or code 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
    Entire
    -0.92
    ExecuteReader
    -0.91
    OCITY
    -0.85
     raiſ
    -0.85
    ImageContext
    -0.85
    IsMutable
    -0.84
    thâu
    -0.82
    ſelf
    -0.81
     Pollack
    -0.81
    SharedDtor
    -0.79
    POSITIVE LOGITS
     PARTS
    1.14
    Parts
    1.13
     parts
    1.11
     Parts
    1.05
     PART
    1.02
    parts
    1.00
    Part
    0.98
    part
    0.94
     Part
    0.93
    PART
    0.90
    Activations Density 0.127%

    No Known Activations