© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4055
    Prev
    Next
    INDEX
    Explanations

    phrases indicating perception, speculation, or evidence of belief

    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
     asla
    -0.54
    otho
    -0.50
    dymyr
    -0.48
     jamais
    -0.46
     supuesto
    -0.45
     VS
    -0.44
     chiesto
    -0.44
     garantiert
    -0.43
     kolay
    -0.43
     principio
    -0.42
    POSITIVE LOGITS
    enumii
    0.97
     ProtoMessage
    0.92
    enumi
    0.86
     MainAxisSize
    0.82
    DockStyle
    0.77
     evidently
    0.76
     snippetHide
    0.76
    apparently
    0.76
    ArrowToggle
    0.75
     виправивши
    0.75
    Activations Density 0.319%

    No Known Activations