© 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. 2124
    Prev
    Next
    INDEX
    Explanations

    clauses that contain negation

    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
    DockStyle
    -0.67
    Embeddable
    -0.67
     cleanly
    -0.60
    PYX
    -0.59
     kokona
    -0.56
     peacefully
    -0.56
    RenderAtEndOf
    -0.56
     tén
    -0.54
    #
    -0.52
     vaan
    -0.52
    POSITIVE LOGITS
     imply
    0.71
     intended
    0.61
    limited
    0.61
     limited
    0.61
    intended
    0.60
    limit
    0.58
     implies
    0.57
    LIMITED
    0.57
     implied
    0.55
    adpleegd
    0.55
    Activations Density 0.072%

    No Known Activations