© 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. 990
    Prev
    Next
    INDEX
    Explanations

    positive adjectives or adverbs like "great", "good", "well", and "nice"

    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
    ORCID
    -0.66
    になりますが
    -0.57
    onymous
    -0.54
    íncia
    -0.50
    UnifiedTopology
    -0.50
     getItemId
    -0.50
    denominator
    -0.49
    mored
    -0.49
     spos
    -0.49
    listdir
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.90
    great
    0.74
     idea
    0.73
     وتسجيلات
    0.71
     deal
    0.69
     trouva
    0.68
    ✨:
    0.67
    idea
    0.66
     <<<<<<<<<<<<<<
    0.65
    GREAT
    0.63
    Activations Density 0.383%

    No Known Activations