© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15700
    Prev
    Next
    INDEX
    Explanations

    references to alkaline substances or solutions used in chemical processes

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ificantly
    -0.64
     Bax
    -0.57
    govine
    -0.56
    ErrUnexpectedEOF
    -0.55
     Baxter
    -0.54
    JAXB
    -0.53
     Gan
    -0.52
    省市镇
    -0.52
    simus
    -0.50
    Gan
    -0.50
    POSITIVE LOGITS
     alkaline
    2.53
     Alkaline
    2.22
     alkali
    1.94
    Alkal
    1.85
     alkal
    1.66
     Alkal
    1.41
     alkalinity
    1.40
     Alkali
    1.36
     alcal
    1.13
    碱
    1.00
    Activations Density 0.004%

    No Known Activations