© 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. 3403
    Prev
    Next
    INDEX
    Explanations

    segments of dialogue involving expressions of fear, frustration, or protests related to specific rules or bans

    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
    imen
    -0.43
    ↵↵
    -0.42
     ​​
    -0.42
    ↵
    -0.42
    ความ
    -0.39
     me
    -0.39
    isse
    -0.38
    rande
    -0.37
    isca
    -0.37
     K
    -0.36
    POSITIVE LOGITS
     للمعارف
    1.14
    RenderAtEndOf
    1.02
    mybatisplus
    0.98
     Normdatei
    0.93
    StoryboardSegue
    0.93
    Personensuche
    0.93
     متعلقه
    0.92
     Мексичка
    0.91
    expandindo
    0.90
     صوتيه
    0.88
    Activations Density 0.316%

    No Known Activations