© 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. 0-RES-MATRYOSHKA-DC
    7. 12470
    Prev
    Next
    INDEX
    Explanations

    references to common modal verbs indicating permission or possibility

    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
     ejus
    -0.85
     purpoſe
    -0.74
     Octave
    -0.69
     ſtate
    -0.68
     dumne
    -0.68
     orgánico
    -0.67
     Bessel
    -0.67
     mikä
    -0.65
     wako
    -0.65
     octaves
    -0.64
    POSITIVE LOGITS
     nemlig
    1.59
     namelijk
    1.45
     bowiem
    1.38
     însă
    1.37
     jednak
    1.33
     därför
    1.33
     totiž
    1.27
     infatti
    1.25
     allerdings
    1.21
     deshalb
    1.21
    Activations Density 0.008%

    No Known Activations