Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 40
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and emotions related to relationships and social interactions

    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
     auffi
    -0.98
     ſtate
    -0.95
     quæ
    -0.94
    ]),
    
    -0.93
     itſelf
    -0.89
    }),
    
    -0.88
     tevens
    -0.88
     themſelves
    -0.85
    ſelf
    -0.84
     geheel
    -0.82
    POSITIVE LOGITS
     guys
    1.02
     really
    0.98
     stuff
    0.94
     thing
    0.91
     you
    0.90
     things
    0.89
     kids
    0.88
     kinda
    0.87
     fucking
    0.85
     somebody
    0.84
    Activations Density 15.999%

    No Known Activations