© 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. 3-RES-MATRYOSHKA-DC
    7. 2520
    Prev
    Next
    INDEX
    Explanations

    conversational language usually found in question answering scenarios

    oai_token-act-pair · gemini-2.0-flash
    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
    '}}
    -0.54
    >());
    -0.52
    '},
    -0.51
    </u>
    -0.48
    "},
    -0.48
    "]=
    -0.48
    TagMode
    -0.47
    )];
    -0.47
    "}}
    -0.46
    </b>
    -0.46
    POSITIVE LOGITS
     Jefus
    0.78
     Majefty
    0.78
    forChild
    0.72
     ſtate
    0.71
     houſe
    0.68
     itſelf
    0.68
     Perſ
    0.67
     pleaſure
    0.67
     Houſe
    0.67
     myſelf
    0.67
    Activations Density 0.424%

    No Known Activations