© 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. 2-RES-MATRYOSHKA-DC
    7. 3148
    Prev
    Next
    INDEX
    Explanations

    references to the blood disorder hemophilia

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stringify
    -0.67
    orphism
    -0.65
    fontaine
    -0.63
     Knowles
    -0.61
     useAppContext
    -0.61
    toMatchSnapshot
    -0.60
    pyplot
    -0.59
    apollo
    -0.59
    oser
    -0.59
    DMETHOD
    -0.58
    POSITIVE LOGITS
     Hem
    2.89
    Hem
    2.89
     hem
    2.88
     haem
    2.23
     HEM
    2.19
    hem
    2.09
    HEM
    1.84
     Haem
    1.66
     hems
    1.53
    Haem
    1.48
    Activations Density 0.024%

    No Known Activations