© 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. 97028
    Prev
    Next
    INDEX
    Explanations

    remind/reminder

    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
     snippetHide
    -0.67
     wireType
    -0.59
     typelib
    -0.59
     doInBackground
    -0.57
    tagHelperRunner
    -0.56
    PYX
    -0.55
    /**
    -0.55
    KURZBESCHREIBUNG
    -0.54
    osoba
    -0.52
    onViewCreated
    -0.52
    POSITIVE LOGITS
     about
    0.63
     that
    0.61
    Again
    0.55
     Again
    0.55
     ότι
    0.54
     rằng
    0.52
     again
    0.52
    heria
    0.51
    észetes
    0.50
     reg
    0.50
    Activations Density 0.020%

    No Known Activations