© 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. 32188
    Prev
    Next
    INDEX
    Explanations

    terms related to medical pathology, specifically tumors and their characteristics

    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
    ntos
    -0.62
    </tfoot>
    -0.60
     وتسجيلات
    -0.60
    annica
    -0.59
    iasis
    -0.55
    DockStyle
    -0.54
    ulite
    -0.53
    rxjs
    -0.52
    eleste
    -0.52
     externa
    -0.51
    POSITIVE LOGITS
    Sucesor
    0.58
    IMPORTED
    0.52
    cional
    0.51
    MessageTagHelper
    0.51
     kasarigan
    0.49
    Alkal
    0.48
    DllImport
    0.47
    سمبر
    0.47
     তারিখ
    0.47
    SizeF
    0.47
    Activations Density 0.011%

    No Known Activations