© 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. 2-RES-MATRYOSHKA-DC
    7. 3771
    Prev
    Next
    INDEX
    Explanations

    instances of encouragement or promotion

    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
    opheles
    -0.64
    span
    -0.62
     kap
    -0.60
    ensen
    -0.57
    ětí
    -0.57
     Spann
    -0.57
    getPackageName
    -0.57
    Carriera
    -0.56
    issi
    -0.55
    otide
    -0.55
    POSITIVE LOGITS
     encourage
    2.67
     encouraged
    2.61
     Encourage
    2.53
     encouragement
    2.50
     encourages
    2.50
     encouraging
    2.42
    Encourage
    2.34
    couraging
    2.19
    encouragement
    2.16
     encourag
    2.00
    Activations Density 0.016%

    No Known Activations