© 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. 15436
    Prev
    Next
    INDEX
    Explanations

    terms related to a broad scope or diversity of topics

    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
    ()]
    -0.70
    axel
    -0.68
    âme
    -0.68
    ərbaycan
    -0.68
    mately
    -0.65
    createCanvas
    -0.65
     виправивши
    -0.65
     BitmapFactory
    -0.64
    SpringRunner
    -0.64
    lenz
    -0.64
    POSITIVE LOGITS
     ſte
    0.91
     WIDE
    0.84
     ſtate
    0.82
     Jefus
    0.81
     ſy
    0.81
     ſtand
    0.81
     Phry
    0.80
     Wide
    0.79
     houſe
    0.79
    Wide
    0.78
    Activations Density 0.009%

    No Known Activations