© 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. 26068
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a high degree or intensity

    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
     Balo
    -0.75
     معد
    -0.74
     scrubs
    -0.73
     scrub
    -0.69
     Administr
    -0.69
     Mabel
    -0.68
     Bartholomew
    -0.68
     Schlu
    -0.68
    thenReturn
    -0.68
    ="@+
    -0.67
    POSITIVE LOGITS
    highly
    0.91
     highly
    0.82
    Highly
    0.82
     Highly
    0.81
     متحده
    0.71
     nakalista
    0.70
    angliski
    0.68
     altamente
    0.68
    heça
    0.68
    InitStruct
    0.67
    Activations Density 0.009%

    No Known Activations