© 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. 2192
    Prev
    Next
    INDEX
    Explanations

    the number zero

    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
     myſelf
    -1.07
     Monfieur
    -1.01
     Theſe
    -0.98
     iſt
    -0.94
     ſeveral
    -0.94
     faſt
    -0.94
     himſelf
    -0.93
     becauſe
    -0.92
     whoſe
    -0.91
     itſelf
    -0.89
    POSITIVE LOGITS
     Pe
    0.53
     T
    0.50
    原始内容存档于
    0.49
    MeasureSpec
    0.47
    xe
    0.47
     b
    0.46
    gebracht
    0.45
     da
    0.44
     y
    0.44
    arpa
    0.44
    Activations Density 0.188%

    No Known Activations