© 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. 24-RES-MATRYOSHKA-DC
    7. 128
    Prev
    Next
    INDEX
    Explanations

    the word "in" (sometimes followed by "to" or "which")

    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.24.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.24.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
    LabelTagHelper
    -0.82
    紹介します
    -0.73
    principalTable
    -0.72
    考える
    -0.69
     Roskov
    -0.66
    目指
    -0.66
    idać
    -0.65
    美国
    -0.65
    neath
    -0.64
    狙
    -0.64
    POSITIVE LOGITS
     accordance
    1.28
     order
    1.21
     addition
    1.16
     relation
    1.16
     conjunction
    1.13
     terms
    1.10
     lieu
    1.09
     response
    1.02
     spite
    1.02
     favor
    0.94
    Activations Density 2.106%

    No Known Activations