© 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. 20148
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags and HTTP headers

    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
    ########.
    -0.69
     Walkover
    -0.61
    GeoNames
    -0.60
    RegistryLite
    -0.60
    AndroidJUnit
    -0.59
    
    -0.57
    rigkeit
    -0.54
     nakalista
    -0.53
    Искәрмәләр
    -0.52
    期刊论文
    -0.52
    POSITIVE LOGITS
     name
    0.66
     useDispatch
    0.62
     Name
    0.57
    ArgsConstructor
    0.57
    voort
    0.56
    addContainerGap
    0.54
    ohs
    0.53
    andExpect
    0.52
     hyper
    0.52
    معلومات
    0.52
    Activations Density 0.003%

    No Known Activations