© 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. 2-RES-MATRYOSHKA-DC
    7. 5509
    Prev
    Next
    INDEX
    Explanations

    requests for friendly and approachable individuals

    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
    InjectAttribute
    -0.62
    клопе
    -0.59
     disambiguazione
    -0.59
    IConfiguration
    -0.55
     Aufs
    -0.55
     knap
    -0.54
     Truths
    -0.54
     Blak
    -0.53
    crackers
    -0.52
     imóvel
    -0.52
    POSITIVE LOGITS
     friendly
    3.34
     Friendly
    3.14
    Friendly
    3.06
    friendly
    3.03
     friendliness
    2.36
     unfriendly
    2.08
     vriende
    1.86
     freundlichen
    1.73
     freundlich
    1.68
    友好
    1.62
    Activations Density 0.111%

    No Known Activations