© 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. 17599
    Prev
    Next
    INDEX
    Explanations

    terms related to overriding and modifying existing settings or behaviors

    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
     OFDb
    -0.59
     SERV
    -0.56
    hålla
    -0.55
     åt
    -0.54
     racc
    -0.52
    érêt
    -0.52
     Reverso
    -0.52
    sej
    -0.51
     monstre
    -0.50
     représ
    -0.50
    POSITIVE LOGITS
     overwrite
    0.88
    GEBURTSDATUM
    0.86
    overwrite
    0.86
     overwritten
    0.84
     overruled
    0.83
     pinulongan
    0.82
    HasBeenSet
    0.79
     overridden
    0.78
    存于互联网档案馆
    0.73
     overriding
    0.72
    Activations Density 0.010%

    No Known Activations