© 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. 103
    Prev
    Next
    INDEX
    Explanations

    code containing hexadecimal values preceded by "x"

    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
     ་་
    -1.05
     ſind
    -0.98
     Beſ
    -0.96
     ―――――
    -0.96
     Theſe
    -0.93
     ſever
    -0.92
     iſt
    -0.91
     ſeveral
    -0.91
     myſelf
    -0.89
     verſ
    -0.86
    POSITIVE LOGITS
     M
    1.30
     S
    1.27
     P
    1.27
     D
    1.25
     C
    1.23
     R
    1.23
     L
    1.22
     B
    1.20
     W
    1.20
     T
    1.17
    Activations Density 10.933%

    No Known Activations