© 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. 44079
    Prev
    Next
    INDEX
    Explanations

    closer look

    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
     resourceCulture
    -1.05
    Personendaten
    -0.84
    HostException
    -0.83
    
    -0.81
     nahilalakip
    -0.75
     שוליים
    -0.74
    __':
    -0.73
    ResumeLayout
    -0.73
    withIdentifier
    -0.73
    AndEndTag
    -0.71
    POSITIVE LOGITS
     wall
    0.52
    inn
    0.49
    land
    0.46
    my
    0.45
     seat
    0.45
     facility
    0.44
    ira
    0.43
     castle
    0.43
     scene
    0.42
    ãy
    0.42
    Activations Density 0.087%

    No Known Activations