© 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. 24-RES-MATRYOSHKA-DC
    7. 123
    Prev
    Next
    INDEX
    Explanations

    sentences that includes various forms of the verb "to be" along with some other word(s).

    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.24.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.24.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
     الحره
    -0.72
    λλά
    -0.65
    ectoria
    -0.65
     fince
    -0.65
     Underlying
    -0.62
     Jefus
    -0.61
    underlying
    -0.60
     dafs
    -0.59
     này
    -0.58
     Theſe
    -0.58
    POSITIVE LOGITS
     not
    1.34
     quite
    1.33
     also
    1.26
     likely
    1.17
     always
    1.12
     considered
    1.09
     certainly
    1.09
     still
    1.09
     generally
    1.08
     actually
    1.07
    Activations Density 5.614%

    No Known Activations