© 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. 12-RES-MATRYOSHKA-DC
    7. 31116
    Prev
    Next
    INDEX
    Explanations

    checks for conditions and assertions related to mathematical statements or theorems

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    RectangleBorder
    -0.91
    +#+#
    -0.91
    fjspx
    -0.91
    tagHelperRunner
    -0.88
    WindowConstants
    -0.85
     المعيارى
    -0.83
    AsUp
    -0.82
    yntaxException
    -0.82
    principalTable
    -0.82
    StoryboardSegue
    -0.80
    POSITIVE LOGITS
     Edizioni
    0.58
    campista
    0.56
     true
    0.55
     paham
    0.54
     True
    0.53
     relevant
    0.53
    nolia
    0.51
    zuführen
    0.49
     actual
    0.49
     impec
    0.49
    Activations Density 0.013%

    No Known Activations