© 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. 1830
    Prev
    Next
    INDEX
    Explanations

    strings of characters that appear to be partial words

    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
    k
    -0.92
    n
    -0.86
    ng
    -0.81
    m
    -0.81
    s
    -0.79
    r
    -0.78
    ling
    -0.77
    t
    -0.77
    p
    -0.77
    ting
    -0.76
    POSITIVE LOGITS
     LDA
    1.09
    XA
    1.05
    SNA
    1.04
     MDA
    1.00
    BCA
    1.00
    annica
    1.00
     EEA
    0.99
     SNA
    0.98
    LDA
    0.98
     ITA
    0.98
    Activations Density 2.146%

    No Known Activations