© 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. 4585
    Prev
    Next
    INDEX
    Explanations

    play

    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
    Grüne
    -0.54
     habido
    -0.52
    TestingModule
    -0.50
    ług
    -0.49
    InvalidProtocol
    -0.49
    trial
    -0.48
    ]',
    -0.47
     with
    -0.47
     vittoria
    -0.47
    NameInMap
    -0.47
    POSITIVE LOGITS
     the
    0.71
    TagMode
    0.66
    GEBURTSDATUM
    0.55
    fjspx
    0.54
    UnknownFieldSet
    0.51
    asteroide
    0.51
    asgi
    0.50
     GenerationType
    0.50
    WebElementEntity
    0.50
    AutoField
    0.48
    Activations Density 0.001%

    No Known Activations