© 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. 6-RES-MATRYOSHKA-DC
    7. 226
    Prev
    Next
    INDEX
    Explanations

    prefixes and suffixes related to medicine, especially treatments

    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
     Efq
    -1.07
     useAuth
    -0.93
     Theſe
    -0.93
     Majefty
    -0.92
     iſt
    -0.90
     itſelf
    -0.90
     ainfi
    -0.81
     Jefus
    -0.81
     Anſ
    -0.81
     Beſ
    -0.79
    POSITIVE LOGITS
     anti
    1.06
     sub
    1.01
     pre
    0.97
     Anti
    0.95
     pseudo
    0.91
     pro
    0.90
    Pre
    0.90
    Anti
    0.90
     inter
    0.88
     trans
    0.88
    Activations Density 3.172%

    No Known Activations