© 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. 2963
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negative outcomes or risks

    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
    tonsoft
    -0.51
    tactos
    -0.51
     proofs
    -0.51
    PLIANCE
    -0.50
     BoxFit
    -0.47
    gettyimages
    -0.47
    KLE
    -0.47
    bcryptjs
    -0.46
    Proof
    -0.46
     flux
    -0.46
    POSITIVE LOGITS
    👎
    0.85
    ніципалі
    0.71
     👎
    0.67
    /*
    0.60
     peggio
    0.60
     disambiguazione
    0.59
     (-)
    0.58
     initComponents
    0.58
     mauvaises
    0.58
    ⓧ
    0.58
    Activations Density 0.733%

    No Known Activations