© 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. 1569
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and other short words such as "the", "a", and "his" which often appear near the word "to",

    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
    satunya
    -0.50
    |()
    -0.46
    cionales
    -0.46
     всем
    -0.41
    ly
    -0.41
     összes
    -0.39
     was
    -0.38
     которого
    -0.38
     spread
    -0.36
    жды
    -0.36
    POSITIVE LOGITS
    IndentedString
    0.99
    LLocation
    0.87
     >=",
    0.84
     ModelExpression
    0.79
    ReusableCell
    0.78
     endforeach
    0.78
    NameInMap
    0.76
    ViewFeatures
    0.75
    jsonwebtoken
    0.75
     EconPapers
    0.75
    Activations Density 0.809%

    No Known Activations