© 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. 23915
    Prev
    Next
    INDEX
    Explanations

    categories related to organizational or institutional types, particularly in finance, law enforcement, education, and military contexts

    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
    GraphicsUnit
    -0.51
    AddHtmlAttribute
    -0.46
     OMITBAD
    -0.43
     دریافت‌شده
    -0.42
    +:+
    -0.40
    |}{}
    -0.38
    ът
    -0.38
     '{@
    -0.38
     آم
    -0.37
     laaj
    -0.36
    POSITIVE LOGITS
     الحره
    1.09
    Autoritní
    0.93
    aarrggbb
    0.86
    SourceChecksum
    0.82
    Personendaten
    0.77
    adaptiveStyles
    0.73
     <<<<<<<<<<<<<<
    0.73
    MessageOf
    0.70
    webElementXpaths
    0.70
    Sqft
    0.69
    Activations Density 0.039%

    No Known Activations