© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23410
    Prev
    Next
    INDEX
    Explanations

    negations or terms indicating absence or lack

    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
    Negative Logits
     Schulze
    -0.66
     Ayres
    -0.66
    ayer
    -0.60
    osy
    -0.60
     Saxe
    -0.59
     Lichten
    -0.59
    IDOS
    -0.58
     Espinosa
    -0.57
    overlapping
    -0.57
    oise
    -0.56
    POSITIVE LOGITS
    }],
    0.96
    
    0.94
     useRef
    0.93
    })));
    0.91
    tanleria
    0.91
    ]")]
    0.91
    Autoritní
    0.91
     مشين
    0.90
    bootstrapcdn
    0.90
    NameInMap
    0.88
    Activations Density 0.017%

    No Known Activations