© 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. 22-RES-MATRYOSHKA-DC
    7. 1213
    Prev
    Next
    INDEX
    Explanations

    instances of failing to do something

    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
    AndEndTag
    -0.70
    IntoConstraints
    -0.56
    BeforeMethod
    -0.54
    shortcuts
    -0.49
    ,$_
    -0.48
    YES
    -0.47
     onlyOwner
    -0.46
    好了
    -0.46
    мум
    -0.46
    ">//
    -0.46
    POSITIVE LOGITS
     miserably
    1.43
     Failure
    1.13
     Fail
    1.12
     failures
    1.08
     failure
    1.07
     fail
    1.07
     fails
    1.05
     Failures
    1.04
    Failure
    1.04
     FAILURE
    1.02
    Activations Density 0.196%

    No Known Activations