© 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. 20-CLT-HP
    7. 72218
    Prev
    Next
    INDEX
    Explanations

    magnetic

    np_max-act-logits · 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
    principalColumn
    -0.46
    Precautionary
    -0.46
    forName
    -0.44
    setDo
    -0.44
     sains
    -0.44
     instala
    -0.43
     doInBackground
    -0.43
     Sambo
    -0.42
     Sinai
    -0.42
     faveur
    -0.41
    POSITIVE LOGITS
    roscopy
    0.52
     resistors
    0.51
    Reentrant
    0.50
    idency
    0.48
    FontAwesome
    0.47
    ipedia
    0.47
    rspec
    0.47
     REA
    0.47
    FunctionFlags
    0.46
     AdapterView
    0.46
    Activations Density 0.001%

    No Known Activations