© 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. 22583
    Prev
    Next
    INDEX
    Explanations

    sections related to mathematical diagrams or structures

    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
    一一
    -0.55
    includegraphics
    -0.53
    handleSubmit
    -0.52
     currentIndex
    -0.52
    COMPARE
    -0.51
     Herzens
    -0.50
     Llew
    -0.49
    OMON
    -0.49
     pictured
    -0.49
     compati
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    0.95
     kasarigan
    0.88
     Roskov
    0.87
    ContentAsync
    0.86
    ftagPool
    0.84
     '\\;'
    0.82
    PerformLayout
    0.82
    ]")]
    0.81
    FontOfSize
    0.80
    Билгалдахарш
    0.77
    Activations Density 0.000%

    No Known Activations