© 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. 22-RES-MATRYOSHKA-DC
    7. 2794
    Prev
    Next
    INDEX
    Explanations

    relative pronouns combined with superlative adjectives

    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.22.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.22.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
     conséquence
    -0.65
     mogelijk
    -0.56
     candidato
    -0.54
     esimer
    -0.54
     candidate
    -0.54
     candidates
    -0.52
     referência
    -0.50
     étapes
    -0.50
     alternatives
    -0.50
    styleType
    -0.50
    POSITIVE LOGITS
    енча
    0.68
    Tikang
    0.65
    ثيق
    0.65
    BorderLayout
    0.64
    MigrationBuilder
    0.63
    Mojo
    0.61
     secret
    0.60
     magic
    0.60
     Mojo
    0.59
     AttributeSet
    0.58
    Activations Density 0.170%

    No Known Activations