© 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. 26799
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to warranties and contractual obligations

    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
    contentLoaded
    -0.49
    ContentAsync
    -0.48
     متعلقه
    -0.46
    Particular
    -0.45
     hinweg
    -0.44
    حياتها
    -0.44
    AndEndTag
    -0.44
     ActionResult
    -0.43
    nextProps
    -0.43
    ueltos
    -0.43
    POSITIVE LOGITS
    Portail
    0.67
     HasFactory
    0.65
    esModule
    0.59
    GEBURTSDATUM
    0.59
    HomeAsUpEnabled
    0.57
     NSCoder
    0.56
    UNCIL
    0.56
    atellite
    0.56
     experiencing
    0.55
    rollment
    0.55
    Activations Density 0.067%

    No Known Activations