© 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. 1762
    Prev
    Next
    INDEX
    Explanations

    the word "end" or a word starting with "end"

    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
    хьтан
    -0.69
    WillAppear
    -0.68
     Roskov
    -0.63
    honneur
    -0.62
     ModelExpression
    -0.59
    photobucket
    -0.57
     knex
    -0.57
    führ
    -0.56
    Revenir
    -0.55
     uuidv
    -0.55
    POSITIVE LOGITS
     End
    0.73
    ToEnd
    0.71
    orses
    0.70
     result
    0.66
     END
    0.64
    ANGER
    0.62
    othermic
    0.60
    angers
    0.60
     end
    0.59
    urable
    0.59
    Activations Density 0.632%

    No Known Activations