© 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. 24-RES-MATRYOSHKA-DC
    7. 1337
    Prev
    Next
    INDEX
    Explanations

    strings of numbers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     للمعارف
    -1.00
     EconPapers
    -0.92
    RectangleBorder
    -0.86
    ArgsConstructor
    -0.84
     HasFactory
    -0.81
    脚注の使い方
    -0.81
     Theſe
    -0.79
     дописавши
    -0.77
    ✨:
    -0.75
     dépens
    -0.74
    POSITIVE LOGITS
    %
    0.85
     total
    0.81
     of
    0.80
     additional
    0.79
     separate
    0.79
     different
    0.77
    +
    0.77
     out
    0.73
     unique
    0.73
     such
    0.70
    Activations Density 1.032%

    No Known Activations