© 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. 153
    Prev
    Next
    INDEX
    Explanations

    relative adjectives or adverbs

    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
     supplémentaire
    -0.85
     termica
    -0.71
     tantum
    -0.66
     potenciales
    -0.65
     dépos
    -0.65
    
    -0.65
     ochi
    -0.64
    دی
    -0.63
     supplémentaires
    -0.63
     majeur
    -0.63
    POSITIVE LOGITS
     likely
    0.76
     interesting
    0.69
     closely
    0.68
     difficult
    0.68
     accurate
    0.67
     powerful
    0.66
     well
    0.65
     important
    0.64
     prolific
    0.63
     flexible
    0.63
    Activations Density 1.050%

    No Known Activations