© 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. 19321
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and their associated risk factors or prognosis indicators

    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
     typically
    -0.45
     Signalez
    -0.39
     /
    -0.36
     ki
    -0.36
    StoryboardSegue
    -0.35
    Miss
    -0.35
     Typically
    -0.35
     Form
    -0.34
    Typically
    -0.34
    rollo
    -0.33
    POSITIVE LOGITS
    RegressionTest
    1.05
    MigrationBuilder
    0.98
     nahilalakip
    0.85
     tartalomajánló
    0.81
    PerformLayout
    0.81
    TargetException
    0.80
    ']))
    0.78
    astify
    0.77
     '\\;'
    0.77
     insuffisamment
    0.73
    Activations Density 0.076%

    No Known Activations