© 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. 5-CLT-HP
    7. 1030
    Prev
    Next
    INDEX
    Explanations

    varied topics

    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
    InvalidProtocol
    -1.06
    UserScript
    -0.79
     AssemblyCompany
    -0.78
     otomatig
    -0.67
     endforeach
    -0.64
    DEVICES
    -0.62
    Kontrola
    -0.60
    ])).
    -0.59
     Infórmanos
    -0.59
    quakes
    -0.59
    POSITIVE LOGITS
     Trotzdem
    0.41
    HasForeignKey
    0.40
    Instead
    0.40
    lexikon
    0.40
     instead
    0.39
     kuitenkin
    0.37
     unlikely
    0.37
    Rather
    0.37
     rather
    0.37
     thôi
    0.36
    Activations Density 0.007%

    No Known Activations