© 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. 20-CLT-HP
    7. 74456
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    SpringBootTest
    -0.60
    HostException
    -0.57
     UserDao
    -0.56
     Metropolitana
    -0.56
     boule
    -0.52
     Granada
    -0.52
    UserDto
    -0.52
    ніципа
    -0.52
    TestingModule
    -0.51
     InputDecoration
    -0.51
    POSITIVE LOGITS
    enumi
    0.55
    ebenarnya
    0.53
     ***!
    0.53
    ăl
    0.44
    ibles
    0.44
     Takes
    0.44
    asty
    0.43
     hanem
    0.43
    Takes
    0.43
     otomatig
    0.42
    Activations Density 0.003%

    No Known Activations