© 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. 26749
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness or positive sentiments

    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
     nakalista
    -0.72
    XmlAccessType
    -0.69
    ########.
    -0.63
    allero
    -0.62
    +:+
    -0.60
     Mandel
    -0.59
    ::::::::
    -0.59
     initComponents
    -0.58
     powerpoint
    -0.58
     Haas
    -0.58
    POSITIVE LOGITS
     glad
    0.95
     Glad
    0.92
    glad
    0.81
    Glad
    0.79
     cesse
    0.77
     GLAD
    0.75
    NewUrlParser
    0.72
     courants
    0.72
    بیشتر
    0.66
     Khusus
    0.66
    Activations Density 0.011%

    No Known Activations