© 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. 948
    Prev
    Next
    INDEX
    Explanations

    the adjective 'good' and sometimes the adjective 'bad'

    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
    InjectAttribute
    -0.67
     viewType
    -0.61
    querySelectorAll
    -0.61
    SuppressLint
    -0.60
     Klee
    -0.56
    TableBody
    -0.56
     Hemis
    -0.55
    invokeLater
    -0.54
    DockStyle
    -0.54
     sánh
    -0.53
    POSITIVE LOGITS
    GOOD
    1.04
     GOOD
    1.00
     Good
    0.98
    Good
    0.97
    good
    0.96
     good
    0.84
     luck
    0.82
    enough
    0.78
     samar
    0.76
    byes
    0.70
    Activations Density 0.136%

    No Known Activations