© 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. 4-CLT-HP
    7. 258
    Prev
    Next
    INDEX
    Explanations

    Legal, news, code snippets

    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
    checking
    -0.59
     checking
    -0.58
    testing
    -0.58
    Source
    -0.57
    lifting
    -0.56
     GLC
    -0.56
    ciled
    -0.55
     insuring
    -0.55
     earning
    -0.55
     raising
    -0.54
    POSITIVE LOGITS
    expandindo
    0.53
    сылкі
    0.53
     broad
    0.50
    CodedInputStream
    0.50
    RegressionTest
    0.49
     rewritten
    0.47
    \{\\
    0.46
     fumée
    0.46
     részt
    0.46
     transcribed
    0.44
    Activations Density 0.030%

    No Known Activations