© 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. 5-CLT-HP
    7. 92608
    Prev
    Next
    INDEX
    Explanations

    mentor

    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
    }))
    -0.63
    EClass
    -0.57
    >);
    -0.51
     ModelExpression
    -0.50
    SpringBootTest
    -0.50
     OFDb
    -0.50
    ]))
    -0.49
    TestingModule
    -0.48
    ########.
    -0.47
    elif
    -0.46
    POSITIVE LOGITS
    complexType
    0.58
    EndContext
    0.56
    initialState
    0.54
     volantes
    0.53
    QtCore
    0.53
    binant
    0.52
     décédé
    0.52
    erialized
    0.51
     teased
    0.50
     lectured
    0.50
    Activations Density 0.001%

    No Known Activations