© 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. 5-CLT-HP
    7. 3859
    Prev
    Next
    INDEX
    Explanations

    mia

    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
    PreferredItem
    -0.89
    cold
    -0.61
     cold
    -0.60
    ArrowToggle
    -0.58
     MenuView
    -0.56
    ModelBuilder
    -0.55
     Cold
    -0.54
    InputTagHelper
    -0.54
     bezeichneter
    -0.54
    SupportActionBar
    -0.53
    POSITIVE LOGITS
     snippetHide
    0.60
    JoinColumn
    0.58
     estimés
    0.56
    ритори
    0.52
    }))
    0.52
     referenties
    0.51
    vités
    0.51
    !(:
    0.50
     levels
    0.49
    )"),
    0.48
    Activations Density 0.001%

    No Known Activations