© 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. 12-RES-MATRYOSHKA-DC
    7. 31049
    Prev
    Next
    INDEX
    Explanations

    exact numerical values and percentages related to statistical results in scientific research

    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
    /
    -0.44
    جع
    -0.43
     pro
    -0.43
     n
    -0.42
    -
    -0.41
    <eos>
    -0.39
     
    -0.39
    i
    -0.39
    מוש
    -0.38
     komen
    -0.37
    POSITIVE LOGITS
     Monfieur
    0.98
     Efq
    0.94
     myſelf
    0.94
     itſelf
    0.89
     Jefus
    0.83
     purpoſe
    0.82
    ^(@)
    0.81
     Houſe
    0.81
     Shakspeare
    0.81
     themſelves
    0.80
    Activations Density 0.017%

    No Known Activations