© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 2670
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe a high degree of something, both positive and negative

    oai_token-act-pair · gemini-2.0-flash
    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
    InjectAttribute
    -0.82
     الحره
    -0.81
    MLLoader
    -0.81
     getItemCount
    -0.81
    Personensuche
    -0.81
    bibfield
    -0.79
    InitVars
    -0.77
     GreatSchools
    -0.76
     ProtoMessage
    -0.76
    httphttps
    -0.75
    POSITIVE LOGITS
    Better
    0.81
    better
    0.76
     easier
    0.70
     Better
    0.70
     better
    0.69
     meglio
    0.66
     mieux
    0.60
     simpler
    0.59
     than
    0.57
     BETTER
    0.57
    Activations Density 0.164%

    No Known Activations