© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 549
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or absence of experiences or feelings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     Muffins
    -0.78
    oliber
    -0.75
    voegd
    -0.75
     Pati
    -0.74
    :]:
    -0.73
    ounid
    -0.73
    raisemb
    -0.73
    TagMode
    -0.72
    värr
    -0.72
    attuale
    -0.71
    POSITIVE LOGITS
    NEVER
    1.48
     Never
    1.47
    never
    1.43
    Never
    1.42
     NEVER
    1.39
     never
    1.38
     EVER
    1.34
     Ever
    1.23
    ever
    1.14
     jamás
    1.14
    Activations Density 0.360%

    No Known Activations