© 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. 2272
    Prev
    Next
    INDEX
    Explanations

    the word 'and', sometimes near the words 'chain', 'made' or 'the'

    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
    周一
    -0.48
     north
    -0.44
    -
    -0.44
     primary
    -0.43
    前端
    -0.42
     input
    -0.42
    INPUT
    -0.41
     North
    -0.41
    PrimaryKey
    -0.41
    </i>
    -0.40
    POSITIVE LOGITS
    setVerticalGroup
    1.43
    AccessorTable
    1.25
    MigrationBuilder
    1.20
    yntaxException
    1.09
     kasarigan
    1.02
     propOrder
    1.02
     CreateTagHelper
    1.02
     oprot
    1.01
     BoxDecoration
    0.99
     <=",
    0.99
    Activations Density 0.700%

    No Known Activations