© 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. 1577
    Prev
    Next
    INDEX
    Explanations

    the need for further research or work

    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
    TagHelper
    -0.59
    ModelBuilder
    -0.48
    infeld
    -0.48
    lusst
    -0.47
    ViewImports
    -0.47
    réhen
    -0.46
     udało
    -0.46
    ोंने
    -0.45
     مُعرِّف
    -0.43
    Dislikes
    -0.42
    POSITIVE LOGITS
     needed
    3.14
     required
    2.81
    needed
    2.77
     necessary
    2.69
     Needed
    2.66
     need
    2.64
    required
    2.45
     Required
    2.42
    Needed
    2.39
     NEEDED
    2.39
    Activations Density 1.762%

    No Known Activations