© 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. 2-RES-MATRYOSHKA-DC
    7. 6897
    Prev
    Next
    INDEX
    Explanations

    mentions of hydrogen

    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
     Meksiku
    -0.92
    MeasureSpec
    -0.84
    ErrorException
    -0.77
    CppMethod
    -0.76
     nakalista
    -0.74
    CloseOperation
    -0.71
     doInBackground
    -0.69
    rrggbb
    -0.69
     InputDecoration
    -0.68
    FontAwesome
    -0.66
    POSITIVE LOGITS
     hydrogen
    2.97
     Hydrogen
    2.59
    Hydrogen
    2.52
    hydrogen
    2.39
     Wasserstoff
    1.91
    氢
    1.44
    氫
    1.20
     HYDRO
    1.16
    rógeno
    0.93
    HYDRO
    0.91
    Activations Density 0.004%

    No Known Activations