© 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. 441
    Prev
    Next
    INDEX
    Explanations

    words related to scientific apparatus, diagnoses, geometry, geology, recreation, religion, farming and chemistry.

    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
    a
    -1.01
    n
    -0.98
    e
    -0.97
    t
    -0.94
     
    -0.93
    p
    -0.92
     P
    -0.88
    y
    -0.88
     S
    -0.88
     m
    -0.88
    POSITIVE LOGITS
     themſelves
    1.88
     myſelf
    1.85
     doubtnut
    1.69
     himſelf
    1.68
     Theſe
    1.67
     Majefty
    1.66
     Efq
    1.62
     pleaſure
    1.62
     ſeveral
    1.59
     Anſ
    1.59
    Activations Density 8.424%

    No Known Activations