© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1165
    Prev
    Next
    INDEX
    Explanations

    intensifiers and words of degree like "very", "so", "much", "far", "little" and comparative 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
    LookAnd
    -0.91
    ientí
    -0.53
     publique
    -0.53
     legendary
    -0.53
     oggi
    -0.52
     enshrined
    -0.52
    avits
    -0.51
     CURIAM
    -0.51
     populer
    -0.51
     officiellement
    -0.50
    POSITIVE LOGITS
     plot
    1.02
     scenes
    1.02
     subplot
    0.95
     storyline
    0.95
     narrative
    0.94
     narration
    0.93
     narr
    0.86
     climax
    0.82
     scene
    0.82
     scènes
    0.82
    Activations Density 1.393%

    No Known Activations