© 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. 24232
    Prev
    Next
    INDEX
    Explanations

    terms related to non-invasive medical procedures

    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
    Esk
    -0.74
    躇
    -0.71
     Cycl
    -0.65
     دام
    -0.62
     Idd
    -0.61
    MEMOR
    -0.59
     IPL
    -0.58
    blon
    -0.56
    ReturnValue
    -0.56
    setFrame
    -0.55
    POSITIVE LOGITS
    invasive
    1.33
     invasive
    1.29
     Invasive
    1.24
    vasive
    1.08
     invas
    1.05
     doInBackground
    0.91
     ¦
    0.87
    ,:);
    0.86
    asive
    0.86
     ostavi
    0.84
    Activations Density 0.002%

    No Known Activations