© 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. 28544
    Prev
    Next
    INDEX
    Explanations

    terms related to life and its complexities

    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
    راه
    -0.49
     preciso
    -0.45
     Geral
    -0.44
     mental
    -0.43
    ൗ
    -0.42
    войства
    -0.42
    Underlying
    -0.42
    getService
    -0.41
    cab
    -0.41
    serviceName
    -0.41
    POSITIVE LOGITS
    tagHelperRunner
    0.92
    Tikang
    0.88
    脚注の使い方
    0.86
     ProtoMessage
    0.86
     Bioaccumulative
    0.78
    ühungen
    0.77
     jadx
    0.74
    UseVisualStyle
    0.71
     pinulongan
    0.71
    SequentialGroup
    0.70
    Activations Density 0.012%

    No Known Activations