© 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. 23781
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to lawsuits and claims

    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
    Ref
    -0.59
    Detected
    -0.48
     står
    -0.46
     campañas
    -0.46
     Ref
    -0.45
    مع
    -0.45
    ref
    -0.45
    l
    -0.44
     hjælpe
    -0.44
     güç
    -0.44
    POSITIVE LOGITS
    脚注の使い方
    1.02
     saites
    0.95
     محفوظة
    0.85
    évaluateur
    0.84
    IntoConstraints
    0.81
     wireType
    0.80
     виправивши
    0.79
    ConstraintMaker
    0.78
     GIPHY
    0.75
     للمعارف
    0.75
    Activations Density 0.014%

    No Known Activations