© 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. 12-RES-MATRYOSHKA-DC
    7. 15475
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and warmth in interpersonal communication

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shit
    -0.56
     below
    -0.53
    下面
    -0.52
    logías
    -0.48
     Scre
    -0.48
     conférences
    -0.48
     bocca
    -0.47
    below
    -0.47
    AutoField
    -0.45
     eccl
    -0.45
    POSITIVE LOGITS
    InjectAttribute
    0.85
    клопе
    0.83
    Parcelize
    0.78
    awtextra
    0.77
    ISupport
    0.76
    DockStyle
    0.68
    SharedCtor
    0.66
    HandleFunc
    0.64
    ])));
    0.63
     kasarigan
    0.62
    Activations Density 0.042%

    No Known Activations