© 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. 9708
    Prev
    Next
    INDEX
    Explanations

    negative sentiments toward political figures and their actions

    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
     EVEN
    -0.51
    INCLUDING
    -0.49
     hi
    -0.48
     snippetHide
    -0.48
     even
    -0.47
     albeit
    -0.47
    Rasp
    -0.46
     pang
    -0.46
     WOR
    -0.46
    @[+][
    -0.45
    POSITIVE LOGITS
    iprot
    0.65
    Rüyada
    0.65
    WithIOException
    0.63
    Whatever
    0.61
     kasarigan
    0.61
     Whatever
    0.60
     חיצוניים
    0.60
     termica
    0.57
     Indep
    0.57
     whatever
    0.55
    Activations Density 0.040%

    No Known Activations