© 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. 30208
    Prev
    Next
    INDEX
    Explanations

    questions that begin with "How can I."

    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
    ftagPool
    -0.79
     ujednoznacz
    -0.75
    ſelf
    -0.71
    mybatisplus
    -0.69
     houſe
    -0.69
     AssemblyCulture
    -0.68
     المعيارى
    -0.67
    EndProject
    -0.67
    είτε
    -0.63
     ſtate
    -0.63
    POSITIVE LOGITS
    reducers
    0.55
    quête
    0.54
    updateTime
    0.54
    arankan
    0.53
    StoryboardSegue
    0.53
    NewUrlParser
    0.51
     Casi
    0.51
     sollen
    0.50
    ="&#
    0.50
    arrant
    0.50
    Activations Density 0.008%

    No Known Activations