© 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. 76754
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     ClassNotFound
    -0.51
    fino
    -0.50
     насељу
    -0.49
     Fino
    -0.47
    
    -0.44
    JOptionPane
    -0.43
    optionalTypeArgs
    -0.43
    offsetof
    -0.42
    BeforeEach
    -0.42
     Recep
    -0.41
    POSITIVE LOGITS
     mud
    0.72
    sedown
    0.59
     muck
    0.56
    ysql
    0.55
    urch
    0.54
    mud
    0.54
     Sign
    0.53
     Wikiseite
    0.52
     cry
    0.52
     Signed
    0.52
    Activations Density 0.000%

    No Known Activations