© 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. 22-RES-MATRYOSHKA-DC
    7. 2807
    Prev
    Next
    INDEX
    Explanations

    code snippets within a program

    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.22.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.22.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
    ↵
    -1.24
    ↵↵
    -0.70
    ↵↵↵
    -0.70
    <eos>
    -0.62
    ↵↵↵↵
    -0.58
    ↵↵↵↵↵
    -0.51
    脚注の使い方
    -0.47
    ...
    -0.47
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.43
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.43
    POSITIVE LOGITS
    ConstraintMaker
    0.76
    ,‎
    0.75
     سكانية
    0.70
     للاسماء
    0.70
     $_"
    0.68
    الدراسه
    0.68
     createSprite
    0.68
    '},
    0.65
     propOrder
    0.64
    SequentialGroup
    0.64
    Activations Density 0.163%

    No Known Activations