© 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. 24-RES-MATRYOSHKA-DC
    7. 438
    Prev
    Next
    INDEX
    Explanations

    words and phrases where hedging or uncertainty are being expressed

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     protoimpl
    -0.60
     AssemblyProduct
    -0.56
    teady
    -0.55
    WSGI
    -0.52
     <<<<<<<<<<<<<<
    -0.51
    cinated
    -0.49
     endforeach
    -0.48
     civilised
    -0.48
    colgroup
    -0.46
    Allowed
    -0.46
    POSITIVE LOGITS
     insufficient
    1.33
     poorly
    1.27
     inadequate
    1.25
     incomplete
    1.22
     incorrect
    1.20
     inadequ
    1.18
     lacks
    1.17
     lacking
    1.16
     inaccurate
    1.16
     incorrectly
    1.16
    Activations Density 6.097%

    No Known Activations