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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4783
    Prev
    Next
    INDEX
    Explanations

    science and technology texts

    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
    RenderAtEndOf
    -0.50
    cok
    -0.47
    subsection
    -0.47
     comprom
    -0.47
    InstanceState
    -0.46
     effort
    -0.46
     trasp
    -0.46
    jut
    -0.44
    araus
    -0.44
    Window
    -0.44
    POSITIVE LOGITS
     мәкал
    0.74
    ReusableCell
    0.65
    principalTable
    0.65
    NameInMap
    0.60
     calendriers
    0.58
    oredCriteria
    0.56
    TestTools
    0.55
    ]$}
    0.55
    StoryboardSegue
    0.54
     Roskov
    0.54
    Activations Density 0.035%

    No Known Activations