© 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. 24-RES-MATRYOSHKA-DC
    7. 1003
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation, question marks, and Christian religious concepts

    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.24.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.24.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
     Anyways
    -0.66
    pecto
    -0.63
     Afterwards
    -0.62
     Subsequent
    -0.60
    Afterwards
    -0.59
    TemporalType
    -0.59
    }>;
    -0.58
     Later
    -0.57
    thâu
    -0.57
    Према
    -0.57
    POSITIVE LOGITS
    People
    0.78
     People
    0.72
     people
    0.64
    Yet
    0.64
     spesso
    0.64
    だからこそ
    0.64
     persino
    0.64
    Люди
    0.63
    Businesses
    0.63
    Nowhere
    0.63
    Activations Density 0.790%

    No Known Activations