© 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. 12-RES-MATRYOSHKA-DC
    7. 30397
    Prev
    Next
    INDEX
    Explanations

    phrases and terms that indicate opinions or perceptions about quality or experiences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    CloseHandle
    -0.62
     noDo
    -0.62
    tovers
    -0.51
    PUBLISHED
    -0.51
    hemiah
    -0.50
    ongi
    -0.49
    orus
    -0.48
    зулта
    -0.48
    Diweddarwch
    -0.48
     GetEnumerator
    -0.48
    POSITIVE LOGITS
     rumored
    0.82
     rumor
    0.78
     rumors
    0.71
     rumour
    0.68
    RegressionTest
    0.64
     Infórmanos
    0.62
    ImageContext
    0.61
     rumoured
    0.60
     allegedly
    0.58
     supposedly
    0.58
    Activations Density 0.089%

    No Known Activations