© 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. 805
    Prev
    Next
    INDEX
    Explanations

    text relating to research study approvals

    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
    assertNull
    -0.47
    unhofer
    -0.43
    φό
    -0.43
    Begriffsklä
    -0.42
    莫
    -0.39
    gyen
    -0.39
    ιώ
    -0.38
    ïti
    -0.38
     Fest
    -0.37
    uración
    -0.36
    POSITIVE LOGITS
     approval
    1.38
     Approval
    1.28
     approvals
    1.21
     approved
    1.20
    approval
    1.19
    Approval
    1.16
     approve
    1.12
     APPROVAL
    1.10
    approved
    1.09
     permission
    1.05
    Activations Density 0.616%

    No Known Activations