© 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. 12-RES-MATRYOSHKA-DC
    7. 4889
    Prev
    Next
    INDEX
    Explanations

    patterns related to mathematical and logical conditions involving negative values and their relationships

    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
    CodeAttribute
    -0.55
    parseDouble
    -0.52
    ardo
    -0.50
     Royal
    -0.48
    stro
    -0.48
     frage
    -0.47
     ø
    -0.46
     nâng
    -0.46
    ongono
    -0.46
    agu
    -0.45
    POSITIVE LOGITS
     négatif
    0.89
    }=-
    0.79
     (−
    0.77
     negativity
    0.77
     negativo
    0.76
     $=-
    0.75
     (-)
    0.74
     NEGATIVE
    0.74
     positifs
    0.73
     positif
    0.73
    Activations Density 0.558%

    No Known Activations