© 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. 2-RES-MATRYOSHKA-DC
    7. 5153
    Prev
    Next
    INDEX
    Explanations

    references to rats

    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
     elä
    -0.74
     prét
    -0.71
     degrés
    -0.70
    publique
    -0.69
     dépens
    -0.69
     infantiles
    -0.68
     débats
    -0.68
    zbęd
    -0.68
     avoient
    -0.67
     remplissage
    -0.66
    POSITIVE LOGITS
     rat
    2.64
     Rat
    2.19
    Rat
    2.13
     rats
    2.13
     Rats
    1.91
    rat
    1.77
    Rats
    1.72
    rats
    1.71
     RAT
    1.57
    RAT
    1.20
    Activations Density 0.014%

    No Known Activations