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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4345
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "custom" and its variations, indicating interests in customization and personalization

    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
    ELTS
    -0.81
     rootReducer
    -0.81
     Gegenteil
    -0.80
     financeira
    -0.79
     MessageBoxIcon
    -0.78
     redraw
    -0.76
    Forums
    -0.76
    twimg
    -0.75
     energética
    -0.75
     Xperia
    -0.73
    POSITIVE LOGITS
     Custom
    1.41
     CUSTOM
    1.36
    Custom
    1.30
    custom
    1.25
     custom
    1.23
    CUSTOM
    1.23
    setCustom
    1.17
     cust
    1.02
    Cust
    1.01
     Cust
    1.01
    Activations Density 0.032%

    No Known Activations