© 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. 39876
    Prev
    Next
    INDEX
    Explanations

    space

    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
     space
    -1.36
    space
    -1.02
     espacio
    -0.94
     ruimte
    -0.91
     espaço
    -0.85
     espace
    -0.84
     Space
    -0.83
    Space
    -0.81
    空间
    -0.81
    espace
    -0.76
    POSITIVE LOGITS
     windings
    0.54
     discontinuities
    0.54
     quarks
    0.53
     argc
    0.52
     bushings
    0.52
    govine
    0.50
    flop
    0.50
     resistors
    0.49
    charge
    0.49
     residues
    0.49
    Activations Density 0.142%

    No Known Activations