© 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. 19574
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate negation or a lack of something

    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
    htë
    -0.63
    TypeDef
    -0.59
    mazon
    -0.55
     all
    -0.54
     mxArray
    -0.53
    makeText
    -0.52
     whether
    -0.51
    i
    -0.51
    USTAIN
    -0.50
     crois
    -0.50
    POSITIVE LOGITS
     Cassini
    0.93
     Houſe
    0.85
    odeon
    0.84
     Heidelberg
    0.82
     houſe
    0.81
     argint
    0.79
     ་་
    0.79
     débats
    0.78
     Nicosia
    0.77
     spé
    0.76
    Activations Density 0.004%

    No Known Activations