© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44175
    Prev
    Next
    INDEX
    Explanations

    Burglary/crime

    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
    الحياه
    -0.73
     kasarigan
    -0.69
    цездатний
    -0.67
    脚注の使い方
    -0.66
    //
    -0.65
     AssemblyCompany
    -0.65
     gynhyrchwyd
    -0.65
    adpleegd
    -0.64
    ftagPool
    -0.64
     يتيمه
    -0.64
    POSITIVE LOGITS
    ized
    0.56
    ists
    0.49
    ckså
    0.48
     órg
    0.46
    ifilm
    0.46
    vlád
    0.45
     olet
    0.45
    ist
    0.45
    scor
    0.44
    帳
    0.44
    Activations Density 1.188%

    No Known Activations