© 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. 17430
    Prev
    Next
    INDEX
    Explanations

    negative numerical values associated with various measurements or scores

    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
    ✨:
    -0.95
     "@/
    -0.92
     Wenger
    -0.88
    évaluateur
    -0.86
     fatis
    -0.85
     purpoſe
    -0.85
     reaſon
    -0.84
     raiſ
    -0.82
     Tallahassee
    -0.81
     juſt
    -0.81
    POSITIVE LOGITS
    )−
    1.05
    −
    1.05
     −
    0.95
     (−
    0.82
    (−
    0.73
    =−
    0.70
    ],
    0.69
    ley
    0.69
    ̃o
    0.67
     Moreno
    0.66
    Activations Density 0.028%

    No Known Activations