© 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. 658
    Prev
    Next
    INDEX
    Explanations

    words generally describing something, along with subjective and comparative terms

    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
     Majefty
    -0.75
     myſelf
    -0.74
     pleaſure
    -0.73
     propOrder
    -0.69
     purpoſe
    -0.68
    ंदीखरीदारी
    -0.65
     houſe
    -0.65
    insegna
    -0.65
    MigrationBuilder
    -0.64
     Monfieur
    -0.64
    POSITIVE LOGITS
     become
    0.86
     available
    0.84
     appear
    0.78
     easier
    0.74
     accessible
    0.70
     feel
    0.69
     look
    0.68
     aware
    0.67
    become
    0.66
    成为
    0.63
    Activations Density 0.507%

    No Known Activations