© 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. 2156
    Prev
    Next
    INDEX
    Explanations

    academic writing, especially physics

    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
     cazul
    -0.54
     comportamento
    -0.49
    يكب
    -0.49
     behaviour
    -0.48
    dataTables
    -0.47
     nakalista
    -0.47
    CppCodeGen
    -0.47
    jfree
    -0.47
     surprising
    -0.46
     ArrayAdapter
    -0.45
    POSITIVE LOGITS
    PageContext
    0.67
    клопе
    0.59
     الكه
    0.58
    NewUrlParser
    0.57
    AsUp
    0.57
    spender
    0.56
    URLException
    0.55
    Personendaten
    0.54
    ProgressHUD
    0.54
    CodeAttribute
    0.53
    Activations Density 0.510%

    No Known Activations