© 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. 17476
    Prev
    Next
    INDEX
    Explanations

    elements of dialogue revealing emotional responses or tension

    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
     AssemblyTitle
    -0.72
    featureID
    -0.67
     <<<<<<<<<<<<<<
    -0.61
    XmlAccessType
    -0.60
    styleType
    -0.59
    principalColumn
    -0.58
    umenten
    -0.58
    
    -0.57
     tegas
    -0.57
    Từ
    -0.55
    POSITIVE LOGITS
     iga
    0.47
     Offisielt
    0.46
     Teich
    0.44
    ⨯
    0.44
     AtomicInteger
    0.44
    นอก
    0.43
     restTemplate
    0.43
    󠁿
    0.42
    որ
    0.42
     Regener
    0.42
    Activations Density 0.056%

    No Known Activations