© 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. 2-RES-MATRYOSHKA-DC
    7. 2778
    Prev
    Next
    INDEX
    Explanations

    references to directional movement or orientation

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Anti
    -0.73
     anti
    -0.72
    oglobulin
    -0.70
     Anti
    -0.69
    trze
    -0.67
    anti
    -0.66
     hoo
    -0.63
     Gough
    -0.62
     fatica
    -0.61
    SequentialGroup
    -0.60
    POSITIVE LOGITS
     toward
    3.17
    toward
    3.05
     towards
    2.97
    towards
    2.86
     Toward
    2.84
     Towards
    2.73
    Towards
    2.66
    Toward
    2.58
     hacia
    1.89
     TOW
    1.89
    Activations Density 0.010%

    No Known Activations