© 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. 1455
    Prev
    Next
    INDEX
    Explanations

    words associated with fixing abstract or physical problems

    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
    ContextHolder
    -0.54
    __(/*!
    -0.51
    ahren
    -0.49
    IsPostBack
    -0.49
     verg
    -0.48
    zot
    -0.47
    ().__
    -0.47
    uxta
    -0.47
     expanded
    -0.45
     Exactos
    -0.44
    POSITIVE LOGITS
     solve
    1.85
     remedy
    1.84
     solving
    1.77
     solves
    1.73
     solved
    1.67
    solve
    1.63
     cure
    1.59
     remedies
    1.59
     Solving
    1.56
     solution
    1.55
    Activations Density 2.870%

    No Known Activations