© 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. 24670
    Prev
    Next
    INDEX
    Explanations

    instances of conflicts of interest

    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
    photobucket
    -0.60
    LEncoder
    -0.57
    })));
    -0.57
    ><!--
    -0.56
    ]))
    -0.56
    ])));
    -0.56
    zzleHttp
    -0.56
    yntaxException
    -0.55
    ]]:
    -0.54
     nonatomic
    -0.54
    POSITIVE LOGITS
    Джерела
    0.48
     nepo
    0.46
     Zugang
    0.46
     ostavi
    0.46
    傾
    0.45
    famili
    0.45
     avantages
    0.44
     Mesopo
    0.43
     CAPE
    0.42
    Manbalar
    0.41
    Activations Density 0.138%

    No Known Activations