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. 23494
    Prev
    Next
    INDEX
    Explanations

    instances of the word "practical."

    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
    oneofs
    -1.00
    NewRow
    -0.87
     Entities
    -0.86
     ModelExpression
    -0.86
    ThroughAttribute
    -0.82
    UnusedPrivate
    -0.81
    RenderAtEndOf
    -0.81
    >{@
    -0.77
    [#
    -0.76
     tủ
    -0.76
    POSITIVE LOGITS
     practical
    0.71
     pragmatic
    0.71
     práctico
    0.71
     prag
    0.69
    practical
    0.69
     Practical
    0.67
     practicality
    0.67
     spirituale
    0.67
     Portail
    0.65
     Valk
    0.63
    Activations Density 0.005%

    No Known Activations