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. 16336
    Prev
    Next
    INDEX
    Explanations

    references to officially recognized historical buildings and their status

    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
    migrationBuilder
    -0.74
     للاسماء
    -0.73
    istemas
    -0.72
    SBATCH
    -0.70
     honours
    -0.68
     ISNI
    -0.68
     />";
    -0.68
     aspen
    -0.68
    IntoConstraints
    -0.66
     prizes
    -0.65
    POSITIVE LOGITS
     listed
    0.54
    ytick
    0.51
    limus
    0.46
    Listing
    0.46
     listing
    0.44
     Listing
    0.43
     فريبيس
    0.42
    bounding
    0.40
    DetailActivity
    0.40
    画
    0.40
    Activations Density 0.009%

    No Known Activations