© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 28075
    Prev
    Next
    INDEX
    Explanations

    negative signs, particularly in mathematical contexts

    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
    Negative Logits
     than
    -0.56
     THAN
    -0.53
     الاطلاع
    -0.50
    hado
    -0.49
    Preced
    -0.48
    certainty
    -0.47
    OrEqualTo
    -0.47
    tso
    -0.46
     Than
    -0.45
    builtins
    -0.45
    POSITIVE LOGITS
     kasarigan
    0.86
     дописавши
    0.86
    GEBURTSDATUM
    0.86
    Хьажоргаш
    0.75
    StructEnd
    0.73
    ⓧ
    0.73
     tartalomajánló
    0.72
    InitVars
    0.71
    celotti
    0.70
    ніципалі
    0.70
    Activations Density 0.039%

    No Known Activations