© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14669
    Prev
    Next
    INDEX
    Explanations

    keywords related to disease classifications and medical guidelines

    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
     Biôgrafia
    -0.49
     <<<<<<<<<<<<<<
    -0.47
    istock
    -0.45
     ApiException
    -0.44
    MOCK
    -0.44
    Indented
    -0.44
    ngdoc
    -0.43
     bedeckt
    -0.42
    as
    -0.40
    IsContent
    -0.40
    POSITIVE LOGITS
    Abraço
    0.64
    ^(@)
    0.64
    $^\
    0.63
    TextWatcher
    0.62
    FTFY
    0.61
    Reprodução
    0.60
    LikeLike
    0.60
    LEncoder
    0.60
     generalization
    0.59
    StoryboardSegue
    0.59
    Activations Density 0.036%

    No Known Activations