© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1125
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the importance of noting specific information or findings

    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
    mergeFrom
    -0.68
    abetes
    -0.68
     autorytatywna
    -0.65
    awtextra
    -0.63
     незавершена
    -0.60
    ])));
    -0.60
    ValueStyle
    -0.59
    Viitteet
    -0.58
    Zubereitung
    -0.58
    deus
    -0.57
    POSITIVE LOGITS
     Note
    1.27
     note
    1.22
    Note
    1.21
     NOTE
    1.16
    NOTE
    1.05
    note
    1.05
     noting
    0.94
     Nota
    0.90
    Nota
    0.90
     Notes
    0.85
    Activations Density 0.549%

    No Known Activations