© 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. 1721
    Prev
    Next
    INDEX
    Explanations

    concepts related to reasonableness and justification, particularly in legal contexts

    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
    XmlAccessorType
    -0.84
    BeginContext
    -0.77
    isContained
    -0.77
    Externí
    -0.75
     незавершена
    -0.69
    principalColumn
    -0.68
    MultipartFile
    -0.67
     Agassi
    -0.66
    fjspx
    -0.65
    ViewChild
    -0.65
    POSITIVE LOGITS
     razonable
    1.10
     raisonnable
    1.09
     REASON
    1.02
     Reason
    0.98
    Reasonable
    0.90
     reasonable
    0.89
     reason
    0.86
     Reasonable
    0.85
     reasons
    0.85
    Reason
    0.85
    Activations Density 0.632%

    No Known Activations