© 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. 0-CLT-HP
    7. 41076
    Prev
    Next
    INDEX
    Explanations

    pass

    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
    pass
    -0.85
    mid
    -0.66
    ,
    -0.61
     
    -0.59
    s
    -0.58
    kot
    -0.56
    .
    -0.54
     I
    -0.53
     but
    -0.50
    /
    -0.50
    POSITIVE LOGITS
     beginnetje
    1.05
    AndEndTag
    1.05
    Personendaten
    1.04
    ]";
    1.03
    __":
    1.02
    ViewFeatures
    0.98
    ########.
    0.97
     متعلقه
    0.94
    AnimationsModule
    0.94
    تقاوى
    0.93
    Activations Density 1.670%

    No Known Activations