© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4088
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and conditions in the context of proofs 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
    ImageContext
    -0.71
     שוליים
    -0.66
     mergeFrom
    -0.62
    FTFY
    -0.58
     createContext
    -0.58
     Wikispecies
    -0.53
    cloudfront
    -0.53
     defaultstate
    -0.51
    }';
    -0.51
    setLayoutManager
    -0.51
    POSITIVE LOGITS
    RegressionTest
    0.52
    Thus
    0.49
    pricht
    0.49
     UIImage
    0.48
     Συ
    0.48
    Оп
    0.48
     MotionEvent
    0.47
     cual
    0.46
    unif
    0.46
    Documented
    0.45
    Activations Density 0.291%

    No Known Activations