© 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. 2422
    Prev
    Next
    INDEX
    Explanations

    the word "is" and words associated with it like "are", or "was" in code and documentation

    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
     Roskov
    -0.60
     Winaray
    -0.56
    </tfoot>
    -0.52
     (;;)
    -0.49
    //-->
    -0.49
     mergeFrom
    -0.48
    osoba
    -0.47
    AnimationsModule
    -0.46
    arrol
    -0.46
    のと
    -0.46
    POSITIVE LOGITS
    migrationBuilder
    0.63
     deprecated
    0.58
     الرياضيه
    0.57
     discouraged
    0.56
    Espèce
    0.55
    abstractmethod
    0.54
     experimental
    0.54
    supposed
    0.53
    omitempty
    0.50
    stuhl
    0.50
    Activations Density 0.320%

    No Known Activations