© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19474
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving logarithms

    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
     aceto
    -0.85
     Hez
    -0.77
    οι
    -0.75
    CppMethod
    -0.75
     Zav
    -0.74
    تفصیلات
    -0.74
    Pang
    -0.74
    sigs
    -0.73
     Metzger
    -0.73
    Konrad
    -0.72
    POSITIVE LOGITS
     ln
    1.15
    ln
    1.05
    __*/
    0.77
    }}/>
    0.73
     lata
    0.71
    ukone
    0.71
     Ln
    0.71
     LN
    0.69
    */].
    0.69
     الوطنيه
    0.69
    Activations Density 0.003%

    No Known Activations