© 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. 26061
    Prev
    Next
    INDEX
    Explanations

    phrases that include personal opinions or beliefs about events or subjects

    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
    PAIGN
    -0.65
    YNAMICS
    -0.45
    sera
    -0.45
     Dalio
    -0.44
    FieldDescriptor
    -0.44
    enoord
    -0.44
     arc
    -0.43
    Twee
    -0.43
    pida
    -0.43
    صة
    -0.43
    POSITIVE LOGITS
    Tikang
    0.78
     transfieras
    0.73
     interviewing
    0.68
     متعلقه
    0.65
     itſelf
    0.63
    interview
    0.63
     nahilalakip
    0.63
     насељу
    0.62
     interview
    0.61
     getItemCount
    0.61
    Activations Density 0.183%

    No Known Activations