© 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. 3727
    Prev
    Next
    INDEX
    Explanations

    variations of phraseology related to "appropriate" or "correct" in the context of asserting correctness or agreement

    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
    endpush
    -0.53
    keits
    -0.49
    juvant
    -0.48
     hasta
    -0.48
    rolid
    -0.47
     I
    -0.46
    liothèque
    -0.46
     hingga
    -0.44
    perative
    -0.44
     jeg
    -0.44
    POSITIVE LOGITS
     Ceux
    1.01
     Inscrivez
    0.88
     αυτά
    0.86
     Theſe
    0.85
     dieß
    0.79
     Ciò
    0.77
     ſame
    0.76
    tersebut
    0.75
     Anſ
    0.74
     تانيه
    0.74
    Activations Density 0.100%

    No Known Activations