© 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. 3-RES-MATRYOSHKA-DC
    7. 1266
    Prev
    Next
    INDEX
    Explanations

    words related to encouraging or requiring action

    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
    setParameter
    -0.71
    id
    -0.60
    SqlClient
    -0.59
     Füße
    -0.56
     competente
    -0.56
     gracilis
    -0.56
    ris
    -0.55
     claims
    -0.55
    }")]
    -0.55
    fe
    -0.54
    POSITIVE LOGITS
     encourage
    1.98
     Encourage
    1.90
    Encourage
    1.88
     encouraged
    1.85
     encouragement
    1.85
     encourages
    1.82
     encouraging
    1.77
     encourag
    1.64
     encou
    1.62
    encouragement
    1.59
    Activations Density 0.938%

    No Known Activations