© 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. 24-RES-MATRYOSHKA-DC
    7. 397
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    SequentialGroup
    -0.91
    <bos>
    -0.84
     للمعارف
    -0.82
     '\\;'
    -0.77
     prochaines
    -0.76
    WriteTagHelper
    -0.72
     MainAxisSize
    -0.69
     transfieras
    -0.69
    存于互联网档案馆
    -0.67
    RectangleBorder
    -0.66
    POSITIVE LOGITS
     four
    2.38
     three
    2.33
     five
    2.31
     six
    2.27
     seven
    2.22
     eight
    2.22
     nine
    2.14
     two
    2.08
     several
    1.85
     eleven
    1.83
    Activations Density 7.322%

    No Known Activations