© 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. 45160
    Prev
    Next
    INDEX
    Explanations

    missions, messages

    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
    mission
    -1.13
     message
    -1.10
     mission
    -1.05
     missions
    -1.04
    message
    -1.02
     messages
    -0.97
     missione
    -0.93
     messaggio
    -0.93
     Messages
    -0.90
     misión
    -0.88
    POSITIVE LOGITS
    ally
    0.84
    ality
    0.71
     to
    0.64
    ary
    0.63
    able
    0.52
    er
    0.51
    ist
    0.51
    al
    0.49
     is
    0.48
     for
    0.48
    Activations Density 0.047%

    No Known Activations