© 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. 4-CLT-HP
    7. 1853
    Prev
    Next
    INDEX
    Explanations

    Mythology/hell references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MouseAdapter
    -0.61
    multer
    -0.53
    onomian
    -0.47
    </h6>
    -0.45
     TableColumn
    -0.44
    发表于
    -0.43
    ();
    -0.43
    `;
    -0.43
    labelControl
    -0.43
    COMPUT
    -0.42
    POSITIVE LOGITS
     Picchu
    0.88
    AsUp
    0.75
     intptr
    0.67
     Heights
    0.63
     Valley
    0.63
    بوابة
    0.63
     poffible
    0.61
    uxxxx
    0.60
     bezeichneter
    0.60
     <<<<<<<<<<<<<<
    0.59
    Activations Density 0.019%

    No Known Activations