© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11102
    Prev
    Next
    INDEX
    Explanations

    terms related to admission and the legal context of evidence in court

    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
    ValueStyle
    -1.01
     ArrayAdapter
    -0.77
     colspan
    -0.74
    AccessorTable
    -0.70
    gecko
    -0.69
    }{
    -0.65
     Ast
    -0.65
    لينكات
    -0.65
    SerializedSize
    -0.63
    bard
    -0.63
    POSITIVE LOGITS
     Admissions
    1.33
     admissions
    1.30
     Admission
    1.22
    Admissions
    1.20
     Admit
    1.16
    Admission
    1.10
     admit
    1.08
     admission
    1.08
     admitted
    1.03
     admitting
    0.99
    Activations Density 0.019%

    No Known Activations