© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 75191
    Prev
    Next
    INDEX
    Explanations

    positive words

    np_max-act-logits · 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
    Records
    -0.98
     Records
    -0.97
     Record
    -0.91
    Datuak
    -0.91
     RECORDS
    -0.89
     '\\;'
    -0.88
    records
    -0.88
     Normdatei
    -0.85
     estekak
    -0.84
     cherchés
    -0.82
    POSITIVE LOGITS
     excellent
    0.47
    Excellent
    0.43
     safety
    0.40
     perfect
    0.38
     Excellent
    0.35
    removeAttr
    0.35
     flawless
    0.35
     ter
    0.34
     ab
    0.33
     human
    0.33
    Activations Density 0.000%

    No Known Activations