© 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. 118
    Prev
    Next
    INDEX
    Explanations

    the combination of the verb "to be" with other verbs, adjectives, or adverbs, sometimes in conjunction with negations.

    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
     dafs
    -0.69
     renunciation
    -0.68
     étoient
    -0.68
     Eſ
    -0.66
     liknande
    -0.66
     avoient
    -0.65
     itſelf
    -0.65
     localisation
    -0.65
     mutagenicity
    -0.63
     Diſ
    -0.63
    POSITIVE LOGITS
     able
    1.47
     aware
    1.25
     willing
    1.20
     unable
    1.20
     afraid
    1.16
     interested
    1.12
     ready
    1.05
     engaged
    1.03
     surprised
    1.03
     looking
    1.01
    Activations Density 2.931%

    No Known Activations