© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19607
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions between people or entities

    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
    AddTagHelper
    -0.56
     חיצוניים
    -0.55
    ]--;
    -0.53
    AddHtmlAttribute
    -0.51
    achite
    -0.50
    jugend
    -0.50
    ]++;
    -0.50
    XmlIgnore
    -0.49
    ésie
    -0.48
     Administrativna
    -0.48
    POSITIVE LOGITS
    Personensuche
    0.78
    
    0.59
    WithIOException
    0.57
    endregion
    0.57
     ihop
    0.51
    Jeografia
    0.51
     Logement
    0.50
    izr
    0.50
     oprot
    0.50
    éroport
    0.48
    Activations Density 0.453%

    No Known Activations