© 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. 18-RES-MATRYOSHKA-DC
    7. 769
    Prev
    Next
    INDEX
    Explanations

    math equations

    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.18.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.18.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
     doInBackground
    -0.60
    awtextra
    -0.52
    mola
    -0.51
    bobox
    -0.48
     Blum
    -0.48
     chúc
    -0.48
    ctivity
    -0.47
    InSection
    -0.47
     Dietz
    -0.47
     RECON
    -0.47
    POSITIVE LOGITS
     derivative
    1.35
     Derivative
    1.23
     derivatives
    1.20
    derivative
    1.18
    Derivative
    1.12
     Derivatives
    1.11
    Differenti
    1.08
     Differenti
    1.06
     differentiation
    1.00
    Deriv
    1.00
    Activations Density 2.135%

    No Known Activations