© 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. 21044
    Prev
    Next
    INDEX
    Explanations

    negative values in mathematical expressions

    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
     Hib
    -0.78
     Bourgoin
    -0.76
    elton
    -0.72
    もちゃ
    -0.70
     @"";
    -0.68
    Geplaatst
    -0.68
    Markus
    -0.68
     Kraus
    -0.67
    fetchall
    -0.67
    ราะ
    -0.66
    POSITIVE LOGITS
    ((-
    0.68
    ggior
    0.56
    iempo
    0.53
    ContentAlignment
    0.53
     Accesat
    0.52
     годи
    0.52
    abras
    0.51
    తి
    0.50
     merid
    0.50
    τεί
    0.49
    Activations Density 0.007%

    No Known Activations