Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14569
    Prev
    Next
    INDEX
    Explanations

    expressions of loyalty or fidelity

    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
    removeAttribute
    -0.55
     المعيارى
    -0.52
     loyal
    -0.52
    tagHelper
    -0.47
    XmlSchema
    -0.47
     PLWABN
    -0.45
     counters
    -0.44
     rire
    -0.44
    IsMutable
    -0.44
    KEYCODE
    -0.43
    POSITIVE LOGITS
     loyalty
    1.57
     Loyalty
    1.48
    loyalty
    1.27
    Loyalty
    1.20
     allegiance
    1.05
     sailor
    0.97
     fidelity
    0.94
     sailors
    0.85
     Treue
    0.81
     Haskell
    0.79
    Activations Density 0.018%

    No Known Activations