© 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. 28280
    Prev
    Next
    INDEX
    Explanations

    words and symbols associated with programming components and structures

    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
    ChildScrollView
    -0.65
     calldata
    -0.64
     nawr
    -0.63
    PRNewswire
    -0.62
    GEBURTSDATUM
    -0.61
    utdown
    -0.61
     AssemblyVersion
    -0.61
    cipline
    -0.60
     NSCoder
    -0.60
     Autorisations
    -0.60
    POSITIVE LOGITS
    #+#
    0.52
     الاطلاع
    0.49
     sake
    0.49
    mergeFrom
    0.49
     ganda
    0.45
     vrou
    0.45
     ungef
    0.44
     subtracted
    0.44
     mụn
    0.44
    Ais
    0.42
    Activations Density 0.002%

    No Known Activations