© 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. 5-CLT-HP
    7. 5612
    Prev
    Next
    INDEX
    Explanations

    sports teams and locations

    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
    },[])
    -0.70
     contextLoads
    -0.68
     AssemblyTitle
    -0.67
     utafitiHapana
    -0.65
    protoimpl
    -0.65
     Wikimedijinoj
    -0.63
    AndEndTag
    -0.62
     سكانية
    -0.62
    ief
    -0.58
     nahilalakip
    -0.58
    POSITIVE LOGITS
    XtraBars
    0.53
     Normdatei
    0.47
    ாள
    0.47
    DatabaseError
    0.45
    miyor
    0.42
     ettei
    0.41
    diğinde
    0.40
    rawDesc
    0.40
    neden
    0.38
    OrNil
    0.38
    Activations Density 0.012%

    No Known Activations