© 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. 22-RES-MATRYOSHKA-DC
    7. 2231
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an error or problem

    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.22.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.22.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
     overrated
    -0.51
     pointless
    -0.48
     meaningless
    -0.47
     insignificant
    -0.45
     unreliable
    -0.45
     inactive
    -0.44
    uden
    -0.44
     București
    -0.43
     illiterate
    -0.43
    abandoned
    -0.43
    POSITIVE LOGITS
     wrong
    1.16
    wrong
    1.02
     Wrong
    0.99
    tagHelperRunner
    0.94
     CreateTagHelper
    0.93
    Wrong
    0.88
    AddTagHelper
    0.88
    StructEnd
    0.84
    expandindo
    0.83
     Roskov
    0.82
    Activations Density 0.073%

    No Known Activations