© 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. 3-RES-MATRYOSHKA-DC
    7. 2847
    Prev
    Next
    INDEX
    Explanations

    words ending in "osis" or "mia", often related to medical conditions, particularly those affecting the blood.

    oai_token-act-pair · gemini-2.0-flash
    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
     itſelf
    -1.06
     Efq
    -0.94
     Theſe
    -0.94
     themſelves
    -0.93
     Houſe
    -0.91
     poffible
    -0.89
     ſeveral
    -0.88
    ſelf
    -0.86
     Monfieur
    -0.84
     myſelf
    -0.83
    POSITIVE LOGITS
    opathy
    0.70
    ništ
    0.69
    vitis
    0.62
    URLException
    0.61
    emia
    0.58
    itis
    0.56
    !("{}",
    0.56
    glycemia
    0.54
    LayoutStyle
    0.53
     consultato
    0.52
    Activations Density 0.335%

    No Known Activations