© 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. 0-CLT-HP
    7. 94675
    Prev
    Next
    INDEX
    Explanations

    vol

    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
     vol
    -1.13
    ubel
    -1.12
    ef
    -0.69
     Mon
    -0.58
     volley
    -0.56
     fra
    -0.55
     comp
    -0.54
     ef
    -0.54
     element
    -0.54
     volume
    -0.54
    POSITIVE LOGITS
     supérieurs
    0.90
     réfugi
    0.79
     déclar
    0.78
     récomp
    0.77
     siguran
    0.75
     storici
    0.74
     rempliss
    0.74
     étoient
    0.71
     quirúrg
    0.71
     verksamhet
    0.70
    Activations Density 0.913%

    No Known Activations