© 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. 14057
    Prev
    Next
    INDEX
    Explanations

    terms related to geological features and formations

    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
    __(/*!
    -0.77
    expandindo
    -0.74
     HasFactory
    -0.72
    PageIndex
    -0.69
    ModelAdmin
    -0.67
     "..\..\..\
    -0.65
     Mixtures
    -0.63
    NUMX
    -0.62
    Portály
    -0.60
    convertView
    -0.60
    POSITIVE LOGITS
     tect
    0.56
    setVerticalGroup
    0.56
     tectonic
    0.54
    Continental
    0.53
    uxe
    0.50
     Tect
    0.50
     continental
    0.50
     arraigned
    0.49
     cuire
    0.48
     regional
    0.46
    Activations Density 0.015%

    No Known Activations