© 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. 4642
    Prev
    Next
    INDEX
    Explanations

    references to purity in various contexts

    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
     Monfieur
    -1.09
     Eisenhower
    -0.96
     Momb
    -0.91
     يتيمه
    -0.88
     Efq
    -0.86
     itſelf
    -0.86
     myſelf
    -0.86
     raiſ
    -0.85
     houſe
    -0.85
     Lothar
    -0.85
    POSITIVE LOGITS
     Pure
    1.70
    pure
    1.60
    Pure
    1.58
     pure
    1.53
     PURE
    1.50
    PURE
    1.41
     murni
    1.29
     Purity
    1.27
    Purity
    1.16
     Pur
    1.16
    Activations Density 0.067%

    No Known Activations