© 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. 30689
    Prev
    Next
    INDEX
    Explanations

    instances of the word "transient" referring to temporary conditions or effects

    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
    cèse
    -0.90
    Tem
    -0.84
     Andromeda
    -0.84
    ειτουργ
    -0.81
    theon
    -0.79
     Fears
    -0.75
     Redondo
    -0.74
     Dox
    -0.73
     Yarmouth
    -0.72
     meglio
    -0.71
    POSITIVE LOGITS
     Tran
    1.02
    Tran
    0.94
    tran
    0.93
    Transient
    0.82
    }';
    0.82
     tran
    0.81
    }>;
    0.80
    $}}
    0.79
    ]));
    0.75
     transi
    0.74
    Activations Density 0.008%

    No Known Activations