© 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. 690
    Prev
    Next
    INDEX
    Explanations

    law firm or legal representative names and locations

    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
     محفوظة
    -0.58
    </thead>
    -0.58
    THISDAY
    -0.53
     BorderRadius
    -0.52
     оригіналу
    -0.50
    快
    -0.50
    khana
    -0.50
     év
    -0.47
     zwi
    -0.46
    فار
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.70
     estimés
    0.69
     legale
    0.67
    RenderAtEndOf
    0.65
    ngdoc
    0.65
     Efq
    0.64
     barrister
    0.64
    tagHelperRunner
    0.64
    LabelTagHelper
    0.63
     representing
    0.62
    Activations Density 0.138%

    No Known Activations