© 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. 11957
    Prev
    Next
    INDEX
    Explanations

    references to an application or module in a code context

    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
    ExecuteReader
    -0.95
    applicable
    -0.90
    Linki
    -0.88
     APPLY
    -0.81
    ]")]
    -0.80
    #+#
    -0.79
    Viited
    -0.79
     nahilalakip
    -0.79
    applied
    -0.78
     Mitter
    -0.77
    POSITIVE LOGITS
     app
    1.11
     App
    1.07
    app
    1.02
    App
    0.96
    getApp
    0.96
    APP
    0.91
     APP
    0.88
     getApp
    0.81
     appName
    0.81
     apps
    0.80
    Activations Density 0.042%

    No Known Activations