© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4828
    Prev
    Next
    INDEX
    Explanations

    references to different types of carcinoma in medical texts

    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
    szön
    -0.72
    ing
    -0.60
    ة
    -0.60
    unknownFields
    -0.60
    zval
    -0.60
    profen
    -0.59
    YOND
    -0.57
    ursal
    -0.57
    ting
    -0.56
    HasAnnotation
    -0.56
    POSITIVE LOGITS
     Carcinoma
    1.10
     carcinoma
    1.08
     carcin
    0.93
     Caruso
    0.81
     Carls
    0.79
     وتسجيلات
    0.77
     */;
    0.76
     Carlin
    0.74
     Carab
    0.73
     figliu
    0.73
    Activations Density 0.007%

    No Known Activations