© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 319
    Prev
    Next
    INDEX
    Explanations

    sentences with some form of the verb "to be"

    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
     successful
    -0.56
    وما
    -0.52
     Previously
    -0.52
    Previously
    -0.52
    appé
    -0.51
     censi
    -0.51
     nhau
    -0.50
    lessly
    -0.50
    že
    -0.50
     overlooked
    -0.50
    POSITIVE LOGITS
     usually
    1.30
     certainly
    1.23
     now
    1.21
     also
    1.21
     probably
    1.16
     undoubtedly
    1.16
     currently
    1.13
    usually
    1.09
     hereby
    1.07
    certainly
    1.07
    Activations Density 1.786%

    No Known Activations