© 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. 5
    Prev
    Next
    INDEX
    Explanations

    equal signs followed by a space and a hexadecimal number

    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
    <bos>
    -1.34
     ―――――
    -1.18
     myſelf
    -1.18
     auffi
    -1.17
     againſt
    -1.16
    ſelf
    -1.14
     pleaſure
    -1.14
     ſche
    -1.13
     itſelf
    -1.13
     ainfi
    -1.11
    POSITIVE LOGITS
     
    1.73
     "
    0.90
     $
    0.90
     “
    0.87
     K
    0.84
     T
    0.84
     L
    0.82
     C
    0.81
     B
    0.80
     P
    0.79
    Activations Density 4.055%

    No Known Activations