© 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. 16693
    Prev
    Next
    INDEX
    Explanations

    references to health and medical conditions related to diseases or treatments

    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
     Monfieur
    -1.52
     myſelf
    -1.47
     ―――――
    -1.45
     Anſ
    -1.40
     itſelf
    -1.40
     doubtnut
    -1.38
     Theſe
    -1.32
     Majefty
    -1.27
     Reſ
    -1.26
     raiſ
    -1.25
    POSITIVE LOGITS
     de
    0.81
     «
    0.79
     -
    0.70
     (
    0.69
    …
    0.68
     N
    0.65
     o
    0.65
    ,
    0.65
    <eos>
    0.65
    ...
    0.64
    Activations Density 1.790%

    No Known Activations