© 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. 0-CLT-HP
    7. 42816
    Prev
    Next
    INDEX
    Explanations

    active or context

    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
    onAttach
    -0.69
     AssemblyCulture
    -0.54
     Biosciences
    -0.54
    principalTable
    -0.51
     sensores
    -0.51
    ientôt
    -0.51
    uminazione
    -0.50
    NSIndexPath
    -0.49
     protocol
    -0.48
     Sciences
    -0.48
    POSITIVE LOGITS
     становника
    0.66
    <bos>
    0.57
    styleType
    0.51
    Spoljašnje
    0.51
    getOptions
    0.49
     Nazis
    0.48
    zeiti
    0.47
     testemun
    0.47
    inher
    0.47
     crucified
    0.46
    Activations Density 0.018%

    No Known Activations