© 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. 22-RES-MATRYOSHKA-DC
    7. 1918
    Prev
    Next
    INDEX
    Explanations

    C code related to I2C communication

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.69
     يتيمه
    -0.56
    RenderAtEndOf
    -0.56
     disambiguazione
    -0.54
    ঙ
    -0.54
    yntaxException
    -0.52
    Geplaatst
    -0.51
     abstrait
    -0.51
    <?
    -0.51
    èdia
    -0.49
    POSITIVE LOGITS
    \{\\
    0.64
    featureID
    0.61
     bit
    0.60
    styleUrls
    0.57
     Rising
    0.57
    ENABLE
    0.56
     Enable
    0.55
     enable
    0.55
     Wester
    0.54
    trise
    0.54
    Activations Density 0.842%

    No Known Activations