© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22525
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as function declarations and return statements

    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
     nakalista
    -0.52
    Affirmed
    -0.51
    saraba
    -0.48
    libft
    -0.47
     pylint
    -0.47
    IUrlHelper
    -0.45
    xfer
    -0.44
    hnung
    -0.44
    MergeFrom
    -0.44
     NgModule
    -0.43
    POSITIVE LOGITS
    #
    0.65
     متعلقه
    0.64
    SourceChecksum
    0.63
     الدولى
    0.60
     iprot
    0.59
    typeorm
    0.59
    "]();
    0.59
    ]}>
    0.58
    
    0.56
     utafitiHapana
    0.56
    Activations Density 0.070%

    No Known Activations