© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2169
    Prev
    Next
    INDEX
    Explanations

    of

    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
    -0.94
    PerformLayout
    -0.82
    AddTagHelper
    -0.69
    ItemBackground
    -0.69
     noDo
    -0.68
    RenderAtEndOf
    -0.65
    UnusedPrivate
    -0.65
     pinulongan
    -0.64
    AnchorStyles
    -0.63
    })`
    -0.63
    POSITIVE LOGITS
     the
    0.93
     his
    0.50
     The
    0.48
     keluarganya
    0.47
     die
    0.46
    toMatchSnapshot
    0.45
    ity
    0.44
    the
    0.43
    society
    0.43
     us
    0.43
    Activations Density 0.002%

    No Known Activations