© 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. 276
    Prev
    Next
    INDEX
    Explanations

    words ending in suffixes such as "-ic", "-al", "-tion", "-ous", "-ster", "-ing", or "-ant".

    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
     ſche
    -1.11
     raiſ
    -1.05
    ſelf
    -1.02
    ſelves
    -1.02
     iſt
    -1.00
     Diſ
    -1.00
     Anſ
    -0.99
     Perſ
    -0.99
     Reſ
    -0.99
     pleaſure
    -0.98
    POSITIVE LOGITS
    󠁿
    0.67
    -
    0.64
    ,
    0.63
    мент
    0.59
    UVWXYZ
    0.57
     하는
    0.57
    ย์
    0.56
    neurial
    0.56
    
    0.56
    tamia
    0.56
    Activations Density 3.168%

    No Known Activations