© 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. 24-RES-MATRYOSHKA-DC
    7. 802
    Prev
    Next
    INDEX
    Explanations

    "#" at the beginning of a line

    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.24.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.24.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
    MergeFrom
    -0.69
    AsUp
    -0.57
    كير
    -0.56
    OutputType
    -0.55
     rhestr
    -0.52
    kháu
    -0.48
    exels
    -0.47
    printStackTrace
    -0.47
    ionato
    -0.46
    สู
    -0.46
    POSITIVE LOGITS
    define
    1.23
    ifdef
    1.07
    ifndef
    0.98
     define
    0.98
    include
    0.97
    endif
    0.92
    undef
    0.88
    elif
    0.87
    if
    0.79
     undef
    0.78
    Activations Density 0.058%

    No Known Activations