© 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. 1510
    Prev
    Next
    INDEX
    Explanations

    references to figures, revisions, companies, parts, and other labels

    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
    Personensuche
    -1.02
    ChildScrollView
    -0.97
     يتيمه
    -0.94
    NewUrlParser
    -0.87
     '\\;'
    -0.82
    findpost
    -0.80
    MigrationBuilder
    -0.78
    󠁴
    -0.78
    TypedDataSet
    -0.75
    +:+
    -0.75
    POSITIVE LOGITS
     B
    2.03
     A
    1.82
     C
    1.77
    B
    1.64
     D
    1.45
    A
    1.42
    C
    1.37
     E
    1.13
    D
    1.10
     А
    1.09
    Activations Density 2.199%

    No Known Activations