© 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. 21464
    Prev
    Next
    INDEX
    Explanations

    terms related to abnormalities or anomalies in medical or scientific contexts

    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
     FormBuilder
    -0.81
    stdc
    -0.78
    ंदीखरीदारी
    -0.74
     estimés
    -0.74
     виправивши
    -0.70
    IVEREF
    -0.69
    SequentialGroup
    -0.67
    Décès
    -0.65
     puertas
    -0.62
     domanda
    -0.60
    POSITIVE LOGITS
     Anomaly
    0.91
     abnormalities
    0.84
     Abnormal
    0.82
     abnormality
    0.81
     anormal
    0.80
     anom
    0.79
     abnormal
    0.78
    omaly
    0.77
    Abnormal
    0.76
     irregularities
    0.75
    Activations Density 0.018%

    No Known Activations