© 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. 1-CLT-HP
    7. 12193
    Prev
    Next
    INDEX
    Explanations

    lynch

    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
    DebuggerStep
    -0.54
    newtheorem
    -0.49
    DebuggerNonUser
    -0.47
    يكية
    -0.45
    rrggbb
    -0.44
     vena
    -0.44
     into
    -0.42
    響
    -0.42
    的说道
    -0.41
     uname
    -0.41
    POSITIVE LOGITS
    __':
    0.83
    TargetException
    0.72
     للمعارف
    0.71
     SafeMath
    0.69
    رشف
    0.66
    GraphicsUnit
    0.64
     estekak
    0.63
     <<<<<<<<<<<<<<
    0.61
     AppCompatTheme
    0.59
    __':
    0.59
    Activations Density 0.044%

    No Known Activations